Related papers: Self-regularised Minimum Latency Training for Stre…
Multi-speaker automatic speech recognition (MS-ASR) faces significant challenges in transcribing overlapped speech, a task critical for applications like meeting transcription and conversational analysis. While serialized output training…
There is growing interest in unifying the streaming and full-context automatic speech recognition (ASR) networks into a single end-to-end ASR model to simplify the model training and deployment for both use cases. While in real-world ASR…
Recognizing overlapping speech from multiple speakers in conversational scenarios is one of the most challenging problem for automatic speech recognition (ASR). Serialized output training (SOT) is a classic method to address multi-talker…
As the context window expands, self-attention increasingly dominates the transformer's inference time. Therefore, accelerating attention computation while minimizing performance degradation is essential for the efficient deployment of Large…
Text to speech (TTS) and automatic speech recognition (ASR) are two dual tasks in speech processing and both achieve impressive performance thanks to the recent advance in deep learning and large amount of aligned speech and text data.…
Recently, data-driven task-oriented dialogue systems have achieved promising performance in English. However, developing dialogue systems that support low-resource languages remains a long-standing challenge due to the absence of…
In this paper, we present MooER, a LLM-based large-scale automatic speech recognition (ASR) / automatic speech translation (AST) model of Moore Threads. A 5000h pseudo labeled dataset containing open source and self collected speech data is…
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…
The performance of automatic speech recognition (ASR) systems has advanced substantially in recent years, particularly for languages for which a large amount of transcribed speech is available. Unfortunately, for low-resource languages,…
For real-world speech recognition applications, noise robustness is still a challenge. In this work, we adopt the teacher-student (T/S) learning technique using a parallel clean and noisy corpus for improving automatic speech recognition…
Automatic speech recognition (ASR) systems based on large language models (LLMs) achieve superior performance by leveraging pretrained LLMs as decoders, but their token-by-token generation mechanism leads to inference latency that grows…
We propose an innovative, learnable two-sided short-time Laplace transform (STLT) mechanism to supplant the traditional self attention in transformer-based LLMs. Our STLT introduces trainable parameters for each Laplace node, enabling…
Intermediate layer output (ILO) regularization by means of multitask training on encoder side has been shown to be an effective approach to yielding improved results on a wide range of end-to-end ASR frameworks. In this paper, we propose a…
Attention is the core mechanism of today's most used architectures for natural language processing and has been analyzed from many perspectives, including its effectiveness for machine translation-related tasks. Among these studies,…
Automatic speech recognition (ASR) systems generate real-time transcriptions but often miss nuances that human interpreters capture. While ASR is useful in many contexts, interpreters-who already use ASR tools such as Dragon-add critical…
This paper addresses automatic quality assessment of spoken language translation (SLT). This relatively new task is defined and formalized as a sequence labeling problem where each word in the SLT hypothesis is tagged as good or bad…
Transformer models have achieved remarkable results in a wide range of applications. However, their scalability is hampered by the quadratic time and memory complexity of the self-attention mechanism concerning the sequence length. This…
Noise-robust automatic speech recognition (ASR) has been commonly addressed by applying speech enhancement (SE) at the waveform level before recognition. However, speech-level enhancement does not always translate into consistent…
Speaker-attributed automatic speech recognition (SA-ASR) aims to transcribe speech while assigning transcripts to the corresponding speakers accurately. Existing methods often rely on complex modular systems or require extensive fine-tuning…
End-to-end approaches for automatic speech recognition (ASR) benefit from directly modeling the probability of the word sequence given the input audio stream in a single neural network. However, compared to conventional ASR systems, these…