Related papers: HyperConformer: Multi-head HyperMixer for Efficien…

Speech recognition is the technology that enables machines to interpret and process human speech, converting spoken language into text or commands. This technology is essential for applications such as virtual assistants, transcription…

Self-supervised learning (SSL) has allowed substantial progress in Automatic Speech Recognition (ASR) performance in low-resource settings. In this context, it has been demonstrated that larger self-supervised feature extractors are crucial…

In this paper, we present Multi-scale Feature Aggregation Conformer (MFA-Conformer), an easy-to-implement, simple but effective backbone for automatic speaker verification based on the Convolution-augmented Transformer (Conformer). The…

This work introduces \emph{cross-attention conformer}, an attention-based architecture for context modeling in speech enhancement. Given that the context information can often be sequential, and of different length as the audio that is to…

End-to-end speech recognition models are improved by incorporating external text sources, typically by fusion with an external language model. Such language models have to be retrained whenever the corpus of interest changes. Furthermore,…

This paper describes noisy speech recognition for an augmented reality headset that helps verbal communication within real multiparty conversational environments. A major approach that has actively been studied in simulated environments is…

Self-supervised learning (SSL) models usually require weeks of pre-training with dozens of high-end GPUs. These models typically have a multi-headed self-attention (MHSA) context encoder. However, MHSA takes quadratic time and space in the…

Considering the bimodal nature of human speech perception, lips, and teeth movement has a pivotal role in automatic speech recognition. Benefiting from the correlated and noise-invariant visual information, audio-visual recognition systems…

Large language model (LLM)-based automatic speech recognition (ASR) achieves strong performance but often incurs high computational costs. This work investigates how to obtain the best LLM-ASR performance efficiently. Through comprehensive…

Recent advances in speech recognition and translation rely on hundreds of thousands of hours of Internet speech data. We argue that state-of-the art accuracy can be reached without relying on web-scale data. Canary - multilingual ASR and…

For supervised speech enhancement, contextual information is important for accurate spectral mapping. However, commonly used deep neural networks (DNNs) are limited in capturing temporal contexts. To leverage long-term contexts for tracking…

Transformer has been successfully applied to speech separation recently with its strong long-dependency modeling capacity using a self-attention mechanism. However, Transformer tends to have heavy run-time costs due to the deep encoder…

In a pipeline speech translation system, automatic speech recognition (ASR) system will transmit errors in recognition to the downstream machine translation (MT) system. A standard machine translation system is usually trained on parallel…

Automatic speech recognition (ASR) models make fewer errors when more surrounding speech information is presented as context. Unfortunately, acquiring a larger future context leads to higher latency. There exists an inevitable trade-off…

Conversational speech normally is embodied with loose syntactic structures at the utterance level but simultaneously exhibits topical coherence relations across consecutive utterances. Prior work has shown that capturing longer context…

A key challenge for automatic speech recognition (ASR) systems is to model the speaker level variability. In this paper, compact speaker dependent learning hidden unit contributions (LHUC) are used to facilitate both speaker adaptive…

Fast Automatic Speech Recognition (ASR) is critical for latency-sensitive applications such as real-time captioning and meeting transcription. However, truly parallel ASR decoding remains challenging due to the sequential nature of…

Encoder-decoder based sequence-to-sequence models have demonstrated state-of-the-art results in end-to-end automatic speech recognition (ASR). Recently, the transformer architecture, which uses self-attention to model temporal context…

Decoding continuous speech from intracortical recordings is a central challenge for brain-computer interfaces (BCIs), with transformative potential for individuals with conditions that impair their ability to speak. While recent…

Streaming automatic speech recognition (ASR) aims to emit each hypothesized word as quickly and accurately as possible, while full-context ASR waits for the completion of a full speech utterance before emitting completed hypotheses. In this…