Results 271 to 280 of about 36,891 (314)
Some of the next articles are maybe not open access.
Interspeech
Whisper is a powerful automatic speech recognition (ASR) model. However, its zero-shot performance on low-resource speech requires further improvement, especially in dysarthric speech recognition (DSR).
Tianyi Tan +6 more
semanticscholar +1 more source
Whisper is a powerful automatic speech recognition (ASR) model. However, its zero-shot performance on low-resource speech requires further improvement, especially in dysarthric speech recognition (DSR).
Tianyi Tan +6 more
semanticscholar +1 more source
Journal of Religion and Health, 2011
Personal recollections are offered in reflection upon the tragedy of 9/11. The outreach efforts of the Blanton-Peale Institute in conjunction with the Health Care Chaplaincy of New York and the Red Cross are recalled by CEO Emeritus, Kathryn Madden. A brief clinical study describes the responses of a young man who was one of only a few persons to make ...
openaire +2 more sources
Personal recollections are offered in reflection upon the tragedy of 9/11. The outreach efforts of the Blanton-Peale Institute in conjunction with the Health Care Chaplaincy of New York and the Red Cross are recalled by CEO Emeritus, Kathryn Madden. A brief clinical study describes the responses of a young man who was one of only a few persons to make ...
openaire +2 more sources
IEEE International Conference on Acoustics, Speech, and Signal Processing
Whisper speech recognition is crucial not only for ensuring privacy in sensitive communications but also for providing a critical communication bridge for patients under vocal restraint and enabling discrete interaction in noise-sensitive environments ...
Cancan Li +6 more
semanticscholar +1 more source
Whisper speech recognition is crucial not only for ensuring privacy in sensitive communications but also for providing a critical communication bridge for patients under vocal restraint and enabling discrete interaction in noise-sensitive environments ...
Cancan Li +6 more
semanticscholar +1 more source
The Journal of the Acoustical Society of America, 1989
Whispering is a common, natural way of reducing speech perceptibility, but whether and how whispering affects consonant identification and the acoustic features presumed important for it in normal speech perception are unknown. In this experiment, untrained listeners identified 18 different whispered initial consonants significantly better than chance ...
openaire +2 more sources
Whispering is a common, natural way of reducing speech perceptibility, but whether and how whispering affects consonant identification and the acoustic features presumed important for it in normal speech perception are unknown. In this experiment, untrained listeners identified 18 different whispered initial consonants significantly better than chance ...
openaire +2 more sources
Probing Whisper for Dysarthric Speech in Detection and Assessment
IEEE International Conference on Acoustics, Speech, and Signal ProcessingLarge-scale end-to-end models such as Whisper have shown strong performance on diverse speech tasks, but their internal behavior on pathological speech remains poorly understood.
Zhengjun Yue +3 more
semanticscholar +1 more source
Whisper Has an Internal Word Aligner
Automatic Speech Recognition & UnderstandingThere is an increasing interest in obtaining accurate word-level timestamps from strong automatic speech recognizers, in particular Whisper. Existing approaches either require additional training or are simply not competitive.
Sung-Lin Yeh, Yen Meng, Hao Tang
semanticscholar +1 more source
Empowering Whisper as a Joint Multi-Talker and Target-Talker Speech Recognition System
InterspeechMulti-talker speech recognition and target-talker speech recognition, both involve transcription in multi-talker contexts, remain significant challenges. However, existing methods rarely attempt to simultaneously address both tasks.
Lingwei Meng +6 more
semanticscholar +1 more source
Fine-tuning Whisper on Low-Resource Languages for Real-World Applications
Swiss Text Analytics ConferenceThis paper presents a new approach to fine-tuning OpenAI's Whisper model for low-resource languages by introducing a novel data generation method that converts sentence-level data into a long-form corpus, using Swiss German as a case study.
Vincenzo Timmel +4 more
semanticscholar +1 more source
Towards Rehearsal-Free Multilingual ASR: A LoRA-based Case Study on Whisper
InterspeechPre-trained multilingual speech foundation models, like Whisper, have shown impressive performance across different languages. However, adapting these models to new or specific languages is computationally extensive and faces catastrophic forgetting ...
Tianyi Xu +6 more
semanticscholar +1 more source
Adopting Whisper for Confidence Estimation
IEEE International Conference on Acoustics, Speech, and Signal ProcessingRecent research on word-level confidence estimation for speech recognition systems has primarily focused on lightweight models known as Confidence Estimation Modules (CEMs), which rely on hand-engineered features derived from Automatic Speech Recognition
Vaibhav Aggarwal +3 more
semanticscholar +1 more source