Related papers: Drax: Speech Recognition with Discrete Flow Matchi…
Sequential recommender systems (SRS) have become a research hotspot due to its power in modeling user dynamic interests and sequential behavioral patterns. To maximize model expressive ability, a default choice is to apply a larger and…
In this work we propose an inference technique, asynchronous revision, to unify streaming and non-streaming speech recognition models. Specifically, we achieve dynamic latency with only one model by using arbitrary right context during…
Compared with automatic speech recognition (ASR), the human auditory system is more adept at handling noise-adverse situations, including environmental noise and channel distortion. To mimic this adeptness, auditory models have been widely…
Artificial neural networks (ANN) have become the mainstream acoustic modeling technique for large vocabulary automatic speech recognition (ASR). A conventional ANN features a multi-layer architecture that requires massive amounts of…
End-to-end (E2E) automatic speech recognition (ASR) can operate in two modes: streaming and non-streaming, each with its pros and cons. Streaming ASR processes the speech frames in real-time as it is being received, while non-streaming ASR…
Discrete speech representations have garnered recent attention for their efficacy in training transformer-based models for various speech-related tasks such as automatic speech recognition (ASR), translation, speaker verification, and joint…
Language models based on discrete diffusion have attracted widespread interest for their potential to provide faster generation than autoregressive models. Despite their promise, these models typically produce samples whose quality sharply…
The autoregressive (AR) models, such as attention-based encoder-decoder models and RNN-Transducer, have achieved great success in speech recognition. They predict the output sequence conditioned on the previous tokens and acoustic encoded…
Neural network pruning compresses automatic speech recognition (ASR) models effectively. However, in multilingual ASR, language-agnostic pruning may lead to severe performance drops on some languages because language-agnostic pruning masks…
Joint optimization of multi-channel front-end and automatic speech recognition (ASR) has attracted much interest. While promising results have been reported for various tasks, past studies on its meeting transcription application were…
Distant speech recognition is a challenge, particularly due to the corruption of speech signals by reverberation caused by large distances between the speaker and microphone. In order to cope with a wide range of reverberations in…
Neural transducer-based systems such as RNN Transducers (RNN-T) for automatic speech recognition (ASR) blend the individual components of a traditional hybrid ASR systems (acoustic model, language model, punctuation model, inverse text…
Automatic speech recognition (ASR) is a relevant area in multiple settings because it provides a natural communication mechanism between applications and users. ASRs often fail in environments that use language specific to particular…
The sequential nature of autoregressive next-token prediction imposes a fundamental speed limit on large language models. While continuous flow models offer a path to parallel generation, they traditionally demand expensive iterative…
Speech-based virtual assistants, such as Amazon Alexa, Google assistant, and Apple Siri, typically convert users' audio signals to text data through automatic speech recognition (ASR) and feed the text to downstream dialog models for…
Speaker-role diarization (RD), such as doctor vs. patient or lawyer vs. client, is practically often more useful than conventional speaker diarization (SD), which assigns only generic labels (speaker-1, speaker-2). The state-of-the-art…
Non-autoregressive Transformers (NATs) are recently applied in direct speech-to-speech translation systems, which convert speech across different languages without intermediate text data. Although NATs generate high-quality outputs and…
Generative target speaker extraction (TSE) methods often produce more natural outputs than predictive models. Recent work based on diffusion or flow matching (FM) typically relies on a small, fixed number of reverse steps with a fixed step…
Diffusion Language Models (DLMs) are rapidly emerging as a powerful and promising alternative to the dominant autoregressive (AR) paradigm. By generating tokens in parallel through an iterative denoising process, DLMs possess inherent…
Discrete diffusion or flow models could enable faster and more controllable sequence generation than autoregressive models. We show that na\"ive linear flow matching on the simplex is insufficient toward this goal since it suffers from…