Results 281 to 290 of about 36,891 (314)
Some of the next articles are maybe not open access.
Deepfake Detection of Singing Voices With Whisper Encodings
IEEE International Conference on Acoustics, Speech, and Signal ProcessingThe deepfake generation of singing vocals is a concerning issue for artists in the music industry. In this work, we propose a singing voice deepfake detection (SVDD) system, which uses noise-variant encodings of open-AI’s Whisper model.
Falguni Sharma, Priyanka Gupta
semanticscholar +1 more source
2023
Whisper is a novella centered on the life of Michel, a listless young man living in Washington D.C. When a beautiful and dangerous woman named Frankie storms into the gas station where he works Michel finds himself set on a path of romantic and sexual misadventure.
openaire +1 more source
Whisper is a novella centered on the life of Michel, a listless young man living in Washington D.C. When a beautiful and dangerous woman named Frankie storms into the gas station where he works Michel finds himself set on a path of romantic and sexual misadventure.
openaire +1 more source
Target Speaker ASR with Whisper
IEEE International Conference on Acoustics, Speech, and Signal ProcessingWe propose a novel approach to enable the use of large, single-speaker ASR models, such as Whisper, for target speaker ASR. The key claim of this method is that it is much easier to model relative differences among speakers by learning to condition on ...
Alexander Polok +5 more
semanticscholar +1 more source
Whister: Using Whisper's representations for Stuttering detection
InterspeechIn this paper, we empirically investigate the influence of different factors on the performance of dysfluency detection. Specifically, we examine the impact of data splits, data quality, and learned representations of large pre-trained models. To conduct
Vrushank Changawala, Frank Rudzicz
semanticscholar +1 more source
Atlanta is primarily a male and heterosexual space. During momentary disruptions of the gender and sexual dynamics that define the series as a whole, queerness as a means of sociopolitical inquiry aids in a larger satirical mission of pointing out such things as the cruel absurdity of the criminal justice system.
openaire +1 more source
openaire +1 more source
CB-Whisper: Contextual Biasing Whisper Using Open-Vocabulary Keyword-Spotting
International Conference on Language Resources and EvaluationEnd-to-end automatic speech recognition (ASR) systems often struggle to recognize rare name entities, such as personal names, organizations and terminologies that are not frequently encountered in the training data. This paper presents Contextual Biasing
Yuang Li +9 more
semanticscholar +1 more source
When Whisper Listens to Aphasia: Advancing Robust Post-Stroke Speech Recognition
InterspeechDespite recent advancements in Automatic Speech Recognition (ASR), its accuracy remains low for pathological speech, thereby limiting AI-based healthcare interventions in such settings.
G. Sanguedolce +4 more
semanticscholar +1 more source
Does Whisper Understand Swiss German? An Automatic, Qualitative, and Human Evaluation
Workshop on NLP for Similar Languages, Varieties and DialectsWhisper is a state-of-the-art automatic speech recognition (ASR) model (Radford et al., 2022). Although Swiss German dialects are allegedly not part of Whisper’s training data, preliminary experiments showed Whisper can transcribe Swiss German quite well,
E. Dolev, C. Lutz, Noemi Aepli
semanticscholar +1 more source
SQ-Whisper: Speaker-Querying Based Whisper Model for Target-Speaker ASR
IEEE Transactions on Audio, Speech, and Language ProcessingBenefiting from massive and diverse data sources, speech foundation models exhibit strong generalization and knowledge transfer capabilities to a wide range of downstream tasks. However, a limitation arises from their exclusive handling of single-speaker
Pengcheng Guo +4 more
semanticscholar +1 more source