6 papers · 1 filter
Speaker Targeting via Self-Speaker Adaptation for Multi-talker ASR
Weiqing Wang, Taejin Park, Ivan Medennikov +6
We propose a self-speaker adaptation method for streaming multi-talker automatic speech recognition (ASR) that eliminates the need for explicit speaker queries. Unlike conventional…
Sortformer: A Novel Approach for Permutation-Resolved Speaker Supervision in Speech-to-Text Systems
Taejin Park, Ivan Medennikov, Kunal Dhawan +6
Sortformer is an encoder-based speaker diarization model designed for supervising speaker tagging in speech-to-text models. Instead of relying solely on permutation invariant loss…
Spectral Codecs: Improving Non-Autoregressive Speech Synthesis with Spectrogram-Based Audio Codecs
Ryan Langman, Ante JukiÄ, Kunal Dhawan +2
Historically, most speech models in machine-learning have used the mel-spectrogram as a speech representation. Recently, discrete audio tokens produced by neural audio codecs have…
META-CAT: Speaker-Informed Speech Embeddings via Meta Information Concatenation for Multi-talker ASR
Jinhan Wang, Weiqing Wang, Kunal Dhawan +7
We propose a novel end-to-end multi-talker automatic speech recognition (ASR) framework that enables both multi-speaker (MS) ASR and target-speaker (TS) ASR. Our proposed model is…
Longer is (Not Necessarily) Stronger: Punctuated Long-Sequence Training for Enhanced Speech Recognition and Translation
Nithin Rao Koluguri, Travis Bartley, Hainan Xu +4
This paper presents a new method for training sequence-to-sequence models for speech recognition and translation tasks. Instead of the traditional approach of training models on sh…
Codec-ASR: Training Performant Automatic Speech Recognition Systems with Discrete Speech Representations
Kunal Dhawan, Nithin Rao Koluguri, Ante JukiÄ +3
Discrete speech representations have garnered recent attention for their efficacy in training transformer-based models for various speech-related tasks such as automatic speech rec…