Related papers: Continuous Streaming Multi-Talker ASR with Dual-pa…

Recently, online end-to-end ASR has gained increasing attention. However, the performance of online systems still lags far behind that of offline systems, with a large gap in quality of recognition. For specific scenarios, we can trade-off…

End-to-end models are fast replacing the conventional hybrid models in automatic speech recognition. Transformer, a sequence-to-sequence model, based on self-attention popularly used in machine translation tasks, has given promising results…

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…

Recent advances in large language models (LLMs) have attracted significant interest in extending their capabilities to multimodal scenarios, particularly for speech-to-speech conversational systems. However, existing multimodal models…

The goal of this paper is to optimize the training process of diffusion-based text-to-speech models. While recent studies have achieved remarkable advancements, their training demands substantial time and computational costs, largely due to…

Recently, the source separation performance was greatly improved by time-domain audio source separation based on dual-path recurrent neural network (DPRNN). DPRNN is a simple but effective model for a long sequential data. While DPRNN is…

Recently, several types of end-to-end speech recognition methods named transformer-transducer were introduced. According to those kinds of methods, transcription networks are generally modeled by transformer-based neural networks, while…

Simultaneous speech translation (SST) outputs translations in parallel with streaming speech input, balancing translation quality and latency. While large language models (LLMs) have been extended to handle the speech modality, streaming…

Conventional spoken language translation (SLT) systems are pipeline based systems, where we have an Automatic Speech Recognition (ASR) system to convert the modality of source from speech to text and a Machine Translation (MT) systems to…

Automatic speech recognition (ASR) is widely used in consumer electronics. ASR greatly improves the utility and accessibility of technology, but usually the output is only word sequences without punctuation. This can result in ambiguity in…

This paper proposes a novel automatic speech recognition (ASR) system that can transcribe individual speaker's speech while identifying whether they are target or non-target speakers from multi-talker overlapped speech. Target-speaker ASR…

Multilingual speech data often suffer from long-tailed language distribution, resulting in performance degradation. However, multilingual text data is much easier to obtain, yielding a more useful general language model. Hence, we are…

Neural speech separation has made remarkable progress and its integration with automatic speech recognition (ASR) is an important direction towards realizing multi-speaker ASR. This work provides an insightful investigation of speech…

Self-supervised learning (SSL) is a long-standing goal for speech processing, since it utilizes large-scale unlabeled data and avoids extensive human labeling. Recent years witness great successes in applying self-supervised learning in…

In this paper, we propose a novel approach for the transcription of speech conversations with natural speaker overlap, from single channel speech recordings. The proposed model is a combination of a speaker diarization system and a hybrid…

Existing multi-channel continuous speech separation (CSS) models are heavily dependent on supervised data - either simulated data which causes data mismatch between the training and real-data testing, or the real transcribed overlapping…

In this paper, we define streaming register transducer (SRT), a one-way, letter-to-letter, transductional machine model for transformations of infinite data words whose data domain forms a linear group. Comparing with existing data word…

Existing Self-Supervised Learning (SSL) models for speech typically process speech signals at a fixed resolution of 20 milliseconds. This approach overlooks the varying informational content present at different resolutions in speech…

Large-scale distributed training of deep acoustic models plays an important role in today's high-performance automatic speech recognition (ASR). In this paper we investigate a variety of asynchronous decentralized distributed training…

Streaming ASR with strict latency constraints is required in many speech recognition applications. In order to achieve the required latency, streaming ASR models sacrifice accuracy compared to non-streaming ASR models due to lack of future…