Wav2Vec2
PulseAugur coverage of Wav2Vec2 — every cluster mentioning Wav2Vec2 across labs, papers, and developer communities, ranked by signal.
7 day(s) with sentiment data
-
New voice anonymization model prioritizes content over realism
A new research paper introduces a voice anonymization model that prioritizes content preservation over realistic speech generation. The model utilizes content embeddings from a pre-trained Wav2Vec2 encoder, which are th…
-
SPARCLE model enhances text-to-speech in low-resource settings
Researchers have introduced SPARCLE, a novel speaker-aware grapheme representation model designed to improve text-to-speech (TTS) synthesis, particularly in low-resource scenarios. Unlike traditional phoneme-based syste…
-
wav2VOT tool uses wav2vec2 for automatic phonetic annotation
Researchers have developed wav2VOT, a new tool that leverages the wav2vec2 large speech model to automatically estimate phonetic features such as voice onset time, closure duration, and burst realization. This tool demo…
-
WavLM advances vocal effort classification with data augmentation
Researchers have advanced speaker-based vocal effort classification by utilizing the WavLM model, outperforming previous approaches like Wav2Vec2 and HuBERT. To combat data scarcity, they systematically studied various …
-
AI tool screens Polish children for speech sound errors
Researchers have developed a screening pipeline to identify speech sound errors in Polish-speaking children, addressing the limited access to specialists. The system utilizes a wav2vec2-based CTC token recognizer combin…
-
WhisperX toolkit offers 70x faster transcription with word-level accuracy
WhisperX is an open-source toolkit that enhances OpenAI's Whisper model by providing highly accurate word-level timestamps and speaker diarization. It achieves this by integrating faster-whisper for batched inference, w…
-
Speech models encode child age/gender in early layers, study finds
Researchers have analyzed how well self-supervised learning (SSL) models capture age and gender information in children's speech. The study focused on four models: Wav2Vec2, HuBERT, Data2Vec, and WavLM, examining their …
-
New research enhances speech recognition for dysarthric individuals
Two new research papers explore methods to improve automatic speech recognition (ASR) for individuals with dysarthria, a speech disorder often caused by neurological conditions. The first paper systematically studies sp…
-
Speech models generalize to recognize rare click consonants
Researchers investigated whether self-supervised speech models can accurately recognize uncommon speech sounds, specifically click consonants found in Khoisan languages. By fine-tuning models like Wav2Vec2 and HuBERT on…
-
ASR models evaluated on Dutch child speech, Whisper-medium leads
A new study published on arXiv evaluates the performance of nine state-of-the-art Automatic Speech Recognition (ASR) models, including Whisper, Parakeet, and Wav2Vec2, on Dutch child speech datasets. The fine-tuned Whis…
-
New Vietnamese ASR uses phoneme-based syllabic modeling
Researchers have developed a novel Syllabic-Structure Decoder for Automatic Speech Recognition (ASR) systems specifically for Vietnamese. This new approach models speech at the phoneme level, explicitly capturing the ph…
-
New benchmark tackles ASR bias in Indic languages
Researchers have developed Vividh-ASR, a new benchmark designed to evaluate automatic speech recognition (ASR) models for Indic languages, specifically Hindi and Malayalam. This benchmark categorizes audio into four tie…