LIVIVO - The Search Portal for Life Sciences

zur deutschen Oberfläche wechseln
Advanced search

Search results

Result 1 - 10 of total 104

Search options

  1. Book ; Online: Investigating Self-supervised Pretraining Frameworks for Pathological Speech Recognition

    Violeta, Lester Phillip / Huang, Wen-Chin / Toda, Tomoki

    2022  

    Abstract: We investigate the performance of self-supervised pretraining frameworks on pathological speech datasets used for automatic speech recognition (ASR). Modern end-to-end models require thousands of hours of data to train well, but only a small number of ... ...

    Abstract We investigate the performance of self-supervised pretraining frameworks on pathological speech datasets used for automatic speech recognition (ASR). Modern end-to-end models require thousands of hours of data to train well, but only a small number of pathological speech datasets are publicly available. A proven solution to this problem is by first pretraining the model on a huge number of healthy speech datasets and then fine-tuning it on the pathological speech datasets. One new pretraining framework called self-supervised learning (SSL) trains a network using only speech data, providing more flexibility in training data requirements and allowing more speech data to be used in pretraining. We investigate SSL frameworks such as the wav2vec 2.0 and WavLM models using different setups and compare their performance with different supervised pretraining setups, using two types of pathological speech, namely, Japanese electrolaryngeal and English dysarthric. Our results show that although SSL has shown success with minimally resourced healthy speech, we do not find this to be the case with pathological speech. The best supervised setup outperforms the best SSL setup by 13.9% character error rate in electrolaryngeal speech and 16.8% word error rate in dysarthric speech.

    Comment: Accepted to INTERSPEECH 2022
    Keywords Computer Science - Sound ; Electrical Engineering and Systems Science - Audio and Speech Processing
    Subject code 006
    Publishing date 2022-03-29
    Publishing country us
    Document type Book ; Online
    Database BASE - Bielefeld Academic Search Engine (life sciences selection)

    Full text online

    More links

    Kategorien

    Inter-library loan at ZB MED

    Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

  2. Article ; Online: Elucidation of scandenolone as anti-cancer activity through impairment of the metabolic and signaling vulnerabilities in prostate cancer.

    Basavaraj, Praveenkumar / Hsieh, Po-Fan / Jiang, Wen-Ping / Bau, Da-Tian / Huang, Guan-Jhong / Huang, Wen-Chin

    Biomedicine & pharmacotherapy = Biomedecine & pharmacotherapie

    2023  Volume 164, Page(s) 114948

    Abstract: Prostate cancer (PCa) is the most prevalent men's cancer in America and Western countries. No effective therapies are currently available for PCa aggressiveness, including castration-resistant progression (CRPC). This study aims at evaluation of the ... ...

    Abstract Prostate cancer (PCa) is the most prevalent men's cancer in America and Western countries. No effective therapies are currently available for PCa aggressiveness, including castration-resistant progression (CRPC). This study aims at evaluation of the prospective efficacy and the molecular mechanism of scandenolone (SCA), a natural isoflavone, in PCa progression. SCA suppressed cell viability and progression and induced apoptosis in PCa cells. SCA inhibited the expression of lipogenesis and cholesterogenesis related key genes. Through inhibition of these metabolic genes, SCA decreased the levels of fatty acids, lipid droplets and cholesterols in PCa cells. Moreover, SCA enhanced the expression of antioxidant factors, including Nrf2, HO-1, catalase and SOD-1, and reduced the ROS levels in PCa cells. Substantially, SCA displayed the potential efficacy on CRPC tumors. This paper offers a new insight into the underlying molecular basis of SCA in PCa cells. By coordinated impairment of the metabolic and signaling vulnerabilities, including lipogenesis, cholesterogenesis, ROS and the AR/PSA axis, SCA could be applied as a novel and promising remedy to cure malignant PCa.
    MeSH term(s) Male ; Humans ; Prostatic Neoplasms, Castration-Resistant/pathology ; Receptors, Androgen/metabolism ; Reactive Oxygen Species/metabolism ; Prospective Studies ; Apoptosis ; Cell Line, Tumor
    Chemical Substances Receptors, Androgen ; Reactive Oxygen Species
    Language English
    Publishing date 2023-05-29
    Publishing country France
    Document type Journal Article
    ZDB-ID 392415-4
    ISSN 1950-6007 ; 0753-3322 ; 0300-0893
    ISSN (online) 1950-6007
    ISSN 0753-3322 ; 0300-0893
    DOI 10.1016/j.biopha.2023.114948
    Database MEDical Literature Analysis and Retrieval System OnLINE

    More links

    Kategorien

    In stock of ZB MED Cologne/Königswinter

    Ud II Zs.198: Show issues Location:
    Je nach Verfügbarkeit (siehe Angabe bei Bestand)
    bis Jg. 2021: Bestellungen von Artikeln über das Online-Bestellformular
    ab Jg. 2022: Lesesaal (EG)

    Order via subito

    This service is chargeable due to the Delivery terms set by subito. Orders including an article and supplementary material will be classified as separate orders. In these cases, fees will be demanded for each order.

  3. Book ; Online: Intermediate Fine-Tuning Using Imperfect Synthetic Speech for Improving Electrolaryngeal Speech Recognition

    Violeta, Lester Phillip / Ma, Ding / Huang, Wen-Chin / Toda, Tomoki

    2022  

    Abstract: Research on automatic speech recognition (ASR) systems for electrolaryngeal speakers has been relatively unexplored due to small datasets. When training data is lacking in ASR, a large-scale pretraining and fine tuning framework is often sufficient to ... ...

    Abstract Research on automatic speech recognition (ASR) systems for electrolaryngeal speakers has been relatively unexplored due to small datasets. When training data is lacking in ASR, a large-scale pretraining and fine tuning framework is often sufficient to achieve high recognition rates; however, in electrolaryngeal speech, the domain shift between the pretraining and fine-tuning data is too large to overcome, limiting the maximum improvement of recognition rates. To resolve this, we propose an intermediate fine-tuning step that uses imperfect synthetic speech to close the domain shift gap between the pretraining and target data. Despite the imperfect synthetic data, we show the effectiveness of this on electrolaryngeal speech datasets, with improvements of 6.1% over the baseline that did not use imperfect synthetic speech. Results show how the intermediate fine-tuning stage focuses on learning the high-level inherent features of the imperfect synthetic data rather than the low-level features such as intelligibility.

    Comment: Accepted to ICASSP 2023
    Keywords Computer Science - Sound ; Electrical Engineering and Systems Science - Audio and Speech Processing
    Publishing date 2022-11-02
    Publishing country us
    Document type Book ; Online
    Database BASE - Bielefeld Academic Search Engine (life sciences selection)

    Full text online

    More links

    Kategorien

    Inter-library loan at ZB MED

    Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

  4. Book ; Online: A Comparative Study of Self-supervised Speech Representation Based Voice Conversion

    Huang, Wen-Chin / Yang, Shu-Wen / Hayashi, Tomoki / Toda, Tomoki

    2022  

    Abstract: We present a large-scale comparative study of self-supervised speech representation (S3R)-based voice conversion (VC). In the context of recognition-synthesis VC, S3Rs are attractive owing to their potential to replace expensive supervised ... ...

    Abstract We present a large-scale comparative study of self-supervised speech representation (S3R)-based voice conversion (VC). In the context of recognition-synthesis VC, S3Rs are attractive owing to their potential to replace expensive supervised representations such as phonetic posteriorgrams (PPGs), which are commonly adopted by state-of-the-art VC systems. Using S3PRL-VC, an open-source VC software we previously developed, we provide a series of in-depth objective and subjective analyses under three VC settings: intra-/cross-lingual any-to-one (A2O) and any-to-any (A2A) VC, using the voice conversion challenge 2020 (VCC2020) dataset. We investigated S3R-based VC in various aspects, including model type, multilinguality, and supervision. We also studied the effect of a post-discretization process with k-means clustering and showed how it improves in the A2A setting. Finally, the comparison with state-of-the-art VC systems demonstrates the competitiveness of S3R-based VC and also sheds light on the possible improving directions.

    Comment: Accepted to IEEE Journal of Selected Topics in Signal Processing. arXiv admin note: substantial text overlap with arXiv:2110.06280
    Keywords Computer Science - Sound ; Computer Science - Machine Learning ; Electrical Engineering and Systems Science - Audio and Speech Processing
    Publishing date 2022-07-09
    Publishing country us
    Document type Book ; Online
    Database BASE - Bielefeld Academic Search Engine (life sciences selection)

    Full text online

    More links

    Kategorien

    Inter-library loan at ZB MED

    Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

  5. Book ; Online: A Comparative Study of Voice Conversion Models with Large-Scale Speech and Singing Data

    Yamamoto, Ryuichi / Yoneyama, Reo / Violeta, Lester Phillip / Huang, Wen-Chin / Toda, Tomoki

    The T13 Systems for the Singing Voice Conversion Challenge 2023

    2023  

    Abstract: This paper presents our systems (denoted as T13) for the singing voice conversion challenge (SVCC) 2023. For both in-domain and cross-domain English singing voice conversion (SVC) tasks (Task 1 and Task 2), we adopt a recognition-synthesis approach with ... ...

    Abstract This paper presents our systems (denoted as T13) for the singing voice conversion challenge (SVCC) 2023. For both in-domain and cross-domain English singing voice conversion (SVC) tasks (Task 1 and Task 2), we adopt a recognition-synthesis approach with self-supervised learning-based representation. To achieve data-efficient SVC with a limited amount of target singer/speaker's data (150 to 160 utterances for SVCC 2023), we first train a diffusion-based any-to-any voice conversion model using publicly available large-scale 750 hours of speech and singing data. Then, we finetune the model for each target singer/speaker of Task 1 and Task 2. Large-scale listening tests conducted by SVCC 2023 show that our T13 system achieves competitive naturalness and speaker similarity for the harder cross-domain SVC (Task 2), which implies the generalization ability of our proposed method. Our objective evaluation results show that using large datasets is particularly beneficial for cross-domain SVC.

    Comment: Accepted to ASRU 2023
    Keywords Electrical Engineering and Systems Science - Audio and Speech Processing ; Computer Science - Computation and Language ; Computer Science - Machine Learning ; Computer Science - Sound ; Electrical Engineering and Systems Science - Signal Processing
    Subject code 006 ; 004
    Publishing date 2023-10-08
    Publishing country us
    Document type Book ; Online
    Database BASE - Bielefeld Academic Search Engine (life sciences selection)

    Full text online

    More links

    Kategorien

    Inter-library loan at ZB MED

    Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

  6. Book ; Online: Improving severity preservation of healthy-to-pathological voice conversion with global style tokens

    Halpern, Bence Mark / Huang, Wen-Chin / Violeta, Lester Phillip / van Son, R. J. J. H. / Toda, Tomoki

    2023  

    Abstract: In healthy-to-pathological voice conversion (H2P-VC), healthy speech is converted into pathological while preserving the identity. The paper improves on previous two-stage approach to H2P-VC where (1) speech is created first with the appropriate severity, ...

    Abstract In healthy-to-pathological voice conversion (H2P-VC), healthy speech is converted into pathological while preserving the identity. The paper improves on previous two-stage approach to H2P-VC where (1) speech is created first with the appropriate severity, (2) then the speaker identity of the voice is converted while preserving the severity of the voice. Specifically, we propose improvements to (2) by using phonetic posteriorgrams (PPG) and global style tokens (GST). Furthermore, we present a new dataset that contains parallel recordings of pathological and healthy speakers with the same identity which allows more precise evaluation. Listening tests by expert listeners show that the framework preserves severity of the source sample, while modelling target speaker's voice. We also show that (a) pathology impacts x-vectors but not all speaker information is lost, (b) choosing source speakers based on severity labels alone is insufficient.

    Comment: 7 pages, 3 figures, 5 tables. Accepted to IEEE Automatic Speech Recognition and Understanding Workshop 2023
    Keywords Computer Science - Sound ; Electrical Engineering and Systems Science - Audio and Speech Processing ; I.2.7
    Subject code 410
    Publishing date 2023-10-04
    Publishing country us
    Document type Book ; Online
    Database BASE - Bielefeld Academic Search Engine (life sciences selection)

    Full text online

    More links

    Kategorien

    Inter-library loan at ZB MED

    Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

  7. Book ; Online: The VoiceMOS Challenge 2023

    Cooper, Erica / Huang, Wen-Chin / Tsao, Yu / Wang, Hsin-Min / Toda, Tomoki / Yamagishi, Junichi

    Zero-shot Subjective Speech Quality Prediction for Multiple Domains

    2023  

    Abstract: We present the second edition of the VoiceMOS Challenge, a scientific event that aims to promote the study of automatic prediction of the mean opinion score (MOS) of synthesized and processed speech. This year, we emphasize real-world and challenging ... ...

    Abstract We present the second edition of the VoiceMOS Challenge, a scientific event that aims to promote the study of automatic prediction of the mean opinion score (MOS) of synthesized and processed speech. This year, we emphasize real-world and challenging zero-shot out-of-domain MOS prediction with three tracks for three different voice evaluation scenarios. Ten teams from industry and academia in seven different countries participated. Surprisingly, we found that the two sub-tracks of French text-to-speech synthesis had large differences in their predictability, and that singing voice-converted samples were not as difficult to predict as we had expected. Use of diverse datasets and listener information during training appeared to be successful approaches.

    Comment: Accepted to ASRU 2023
    Keywords Electrical Engineering and Systems Science - Audio and Speech Processing
    Publishing date 2023-10-04
    Publishing country us
    Document type Book ; Online
    Database BASE - Bielefeld Academic Search Engine (life sciences selection)

    Full text online

    More links

    Kategorien

    Inter-library loan at ZB MED

    Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

  8. Book ; Online: The Singing Voice Conversion Challenge 2023

    Huang, Wen-Chin / Violeta, Lester Phillip / Liu, Songxiang / Shi, Jiatong / Toda, Tomoki

    2023  

    Abstract: We present the latest iteration of the voice conversion challenge (VCC) series, a bi-annual scientific event aiming to compare and understand different voice conversion (VC) systems based on a common dataset. This year we shifted our focus to singing ... ...

    Abstract We present the latest iteration of the voice conversion challenge (VCC) series, a bi-annual scientific event aiming to compare and understand different voice conversion (VC) systems based on a common dataset. This year we shifted our focus to singing voice conversion (SVC), thus named the challenge the Singing Voice Conversion Challenge (SVCC). A new database was constructed for two tasks, namely in-domain and cross-domain SVC. The challenge was run for two months, and in total we received 26 submissions, including 2 baselines. Through a large-scale crowd-sourced listening test, we observed that for both tasks, although human-level naturalness was achieved by the top system, no team was able to obtain a similarity score as high as the target speakers. Also, as expected, cross-domain SVC is harder than in-domain SVC, especially in the similarity aspect. We also investigated whether existing objective measurements were able to predict perceptual performance, and found that only few of them could reach a significant correlation.
    Keywords Computer Science - Sound ; Computer Science - Computation and Language ; Electrical Engineering and Systems Science - Audio and Speech Processing
    Subject code 303
    Publishing date 2023-06-26
    Publishing country us
    Document type Book ; Online
    Database BASE - Bielefeld Academic Search Engine (life sciences selection)

    Full text online

    More links

    Kategorien

    Inter-library loan at ZB MED

    Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

  9. Article: ADAM9 drives the immunosuppressive microenvironment by cholesterol biosynthesis-mediated activation of IL6-STAT3 signaling for lung tumor progression.

    Liu, Jing-Pei / Shen, Kuan-Yin / Cheng, Wei-Chung / Chang, Wei-Chao / Hsieh, Chih-Ying / Lo, Chia-Chien / Kuo, Ting-Ting / Lin, Ching-Chan / Liu, Shih-Jen / Huang, Wen-Chin / Sher, Yuh-Pyng

    American journal of cancer research

    2024  Volume 14, Issue 4, Page(s) 1850–1865

    Abstract: Chronic inflammation associated with lung cancers contributes to immunosuppressive tumor microenvironments, reducing ... ...

    Abstract Chronic inflammation associated with lung cancers contributes to immunosuppressive tumor microenvironments, reducing CD8
    Language English
    Publishing date 2024-04-15
    Publishing country United States
    Document type Journal Article
    ZDB-ID 2589522-9
    ISSN 2156-6976
    ISSN 2156-6976
    DOI 10.62347/LODV2387
    Database MEDical Literature Analysis and Retrieval System OnLINE

    More links

    Kategorien

    Order via subito

    This service is chargeable due to the Delivery terms set by subito. Orders including an article and supplementary material will be classified as separate orders. In these cases, fees will be demanded for each order.

  10. Article ; Online: Genetic Suppression of mTOR Rescues Synaptic and Social Behavioral Abnormalities in a Mouse Model of Pten Haploinsufficiency.

    Huang, Wen-Chin / Chen, Youjun / Page, Damon T

    Autism research : official journal of the International Society for Autism Research

    2019  Volume 12, Issue 10, Page(s) 1463–1471

    Abstract: Heterozygous mutations in PTEN, which encodes a negative regulator of the mTOR and β-catenin signaling pathways, cause macrocephaly/autism syndrome. However, the neurobiological substrates of the core symptoms of this syndrome are poorly understood. Here, ...

    Abstract Heterozygous mutations in PTEN, which encodes a negative regulator of the mTOR and β-catenin signaling pathways, cause macrocephaly/autism syndrome. However, the neurobiological substrates of the core symptoms of this syndrome are poorly understood. Here, we investigate the relationship between cerebral cortical overgrowth and social behavior deficits in conditional Pten heterozygous female mice (Pten cHet) using Emx1-Cre, which is expressed in cortical pyramidal neurons and a subset of glia. We found that conditional heterozygous mutation of Ctnnb1 (encoding β-catenin) suppresses Pten cHet cortical overgrowth, but not social behavioral deficits, whereas conditional heterozygous mutation of Mtor suppresses social behavioral deficits, but not cortical overgrowth. Neuronal activity in response to social cues and excitatory synapse markers are elevated in the medial prefrontal cortex (mPFC) of Pten cHet mice, and heterozygous mutation in Mtor, but not Ctnnb1, rescues these phenotypes. These findings indicate that macroscale cerebral cortical overgrowth and social behavioral phenotypes caused by Pten haploinsufficiency can be dissociated based on responsiveness to genetic suppression of Ctnnb1 or Mtor. Furthermore, neuronal connectivity appears to be one potential substrate for mTOR-mediated suppression of social behavioral deficits in Pten haploinsufficient mice. Autism Res 2019, 12: 1463-1471. © 2019 International Society for Autism Research, Wiley Periodicals, Inc. LAY SUMMARY: A subgroup of individuals with autism display overgrowth of the head and the brain during development. Using a mouse model of an autism risk gene, Pten, that displays both brain overgrowth and social behavioral deficits, we show here that that these two symptoms can be dissociated. Reversal of social behavioral deficits in this model is associated with rescue of abnormal synaptic markers and neuronal activity.
    MeSH term(s) Animals ; Behavior, Animal ; Disease Models, Animal ; Female ; Haploinsufficiency/genetics ; Male ; Mice ; PTEN Phosphohydrolase/genetics ; Signal Transduction/genetics ; Suppression, Genetic/genetics ; Synapses/genetics ; TOR Serine-Threonine Kinases/genetics
    Chemical Substances mTOR protein, mouse (EC 2.7.1.1) ; TOR Serine-Threonine Kinases (EC 2.7.11.1) ; PTEN Phosphohydrolase (EC 3.1.3.67) ; Pten protein, mouse (EC 3.1.3.67)
    Language English
    Publishing date 2019-08-23
    Publishing country United States
    Document type Journal Article ; Research Support, N.I.H., Extramural ; Research Support, Non-U.S. Gov't
    ZDB-ID 2481338-2
    ISSN 1939-3806 ; 1939-3792
    ISSN (online) 1939-3806
    ISSN 1939-3792
    DOI 10.1002/aur.2186
    Database MEDical Literature Analysis and Retrieval System OnLINE

    Full text online

    More links

    Kategorien

    In stock of ZB MED Cologne/Königswinter

    Zs.A 6785: Show issues Location:
    Je nach Verfügbarkeit (siehe Angabe bei Bestand)
    bis Jg. 2021: Bestellungen von Artikeln über das Online-Bestellformular
    ab Jg. 2022: Lesesaal (EG)

    Order via subito

    This service is chargeable due to the Delivery terms set by subito. Orders including an article and supplementary material will be classified as separate orders. In these cases, fees will be demanded for each order.

To top