相关论文: Streaming Multi-talker Speech Recognition with Joi…

Streaming Speech-to-Text Translation (StreamST) requires producing translations concurrently with incoming speech, imposing strict latency constraints and demanding models that balance partial-information decision-making with high…

Transformer has shown advanced performance in speech separation, benefiting from its ability to capture global features. However, capturing local features and channel information of audio sequences in speech separation is equally important.…

Streaming speech translation (StreamST) requires determining appropriate timing, known as policy, to generate translations while continuously receiving source speech inputs, balancing low latency with high translation quality. However,…

In recent years, many deep learning techniques for single-channel sound source separation have been proposed using recurrent, convolutional and transformer networks. When multiple microphones are available, spatial diversity between…

Simultaneous speech-to-speech translation (Simul-S2ST, a.k.a streaming speech translation) outputs target speech while receiving streaming speech inputs, which is critical for real-time communication. Beyond accomplishing translation…

Recently in speaker recognition, performance degradation due to the channel domain mismatched condition has been actively addressed. However, the mismatches arising from language is yet to be sufficiently addressed. This paper proposes an…

Target speech separation refers to extracting a target speaker's voice from an overlapped audio of simultaneous talkers. Previously the use of visual modality for target speech separation has demonstrated great potentials. This work…

Transcribing and understanding multi-speaker conversations requires speech recognition, speaker attribution, and timestamp localization. While speech LLMs excel at single-speaker tasks, multi-speaker scenarios remain challenging due to…

Speech applications dealing with conversations require not only recognizing the spoken words, but also determining who spoke when. The task of assigning words to speakers is typically addressed by merging the outputs of two separate…

This paper tackles several challenges that arise when integrating Automatic Speech Recognition (ASR) and Machine Translation (MT) for real-time, on-device streaming speech translation. Although state-of-the-art ASR systems based on…

A key challenge in machine learning is to generalize from training data to an application domain of interest. This work generalizes the recently-proposed mixture invariant training (MixIT) algorithm to perform unsupervised learning in the…

Lipreading refers to understanding and further translating the speech of a speaker in the video into natural language. State-of-the-art lipreading methods excel in interpreting overlap speakers, i.e., speakers appear in both training and…

We introduce the Globally Normalized Autoregressive Transducer (GNAT) for addressing the label bias problem in streaming speech recognition. Our solution admits a tractable exact computation of the denominator for the sequence-level…

Using end-to-end models for speech translation (ST) has increasingly been the focus of the ST community. These models condense the previously cascaded systems by directly converting sound waves into translated text. However, cascaded models…

We propose Speaker-Conditioned Serialized Output Training (SC-SOT), an enhanced SOT-based training for E2E multi-talker ASR. We first probe how SOT handles overlapped speech, and we found the decoder performs implicit speaker separation. We…

Overlapped speech is notoriously problematic for speaker diarization systems. Consequently, the use of speech separation has recently been proposed to improve their performance. Although promising, speech separation models struggle with…

This paper investigates four types of cross-utterance speech contexts modeling approaches for streaming and non-streaming Conformer-Transformer (C-T) ASR systems: i) input audio feature concatenation; ii) cross-utterance Encoder embedding…

Cascaded speech-to-speech translation systems often suffer from the error accumulation problem and high latency, which is a result of cascaded modules whose inference delays accumulate. In this paper, we propose a transducer-based speech…

While large language models (LLMs) have been applied to automatic speech recognition (ASR), the task of making the model streamable remains a challenge. This paper proposes a novel model architecture, Transducer-Llama, that integrates LLMs…

Recently, Transformer based end-to-end models have achieved great success in many areas including speech recognition. However, compared to LSTM models, the heavy computational cost of the Transformer during inference is a key issue to…