相关论文: Turn-Taking Prediction for Natural Conversational …

Stuttering -- characterized by involuntary disfluencies such as blocks, prolongations, and repetitions -- is often misinterpreted by automatic speech recognition (ASR) systems, resulting in elevated word error rates and making voice-driven…

Non-autoregressive (NAR) modeling has gained more and more attention in speech processing. With recent state-of-the-art attention-based automatic speech recognition (ASR) structure, NAR can realize promising real-time factor (RTF)…

Turn-taking is a fundamental mechanism in human communication that ensures smooth and coherent verbal interactions. Recent advances in Large Language Models (LLMs) have motivated their use in improving the turn-taking capabilities of Spoken…

The recent wave of audio foundation models (FMs) could provide new capabilities for conversational modeling. However, there have been limited efforts to evaluate these audio FMs comprehensively on their ability to have natural and…

Interactive voice assistants have been widely used as input interfaces in various scenarios, e.g. on smart homes devices, wearables and on AR devices. Detecting the end of a speech query, i.e. speech end-pointing, is an important task for…

Recently, end-to-end (E2E) automatic speech recognition (ASR) systems have garnered tremendous attention because of their great success and unified modeling paradigms in comparison to conventional hybrid DNN-HMM ASR systems. Despite the…

Language Models (LMs) have been ubiquitously leveraged in various tasks including spoken language understanding (SLU). Spoken language requires careful understanding of speaker interactions, dialog states and speech induced multimodal…

This paper presents a novel streaming end-to-end target-speaker speech recognition that addresses two critical limitations in systems: the handling of noisy enrollment utterances and specific enrollment phrase requirements. This paper…

While standard speaker diarization attempts to answer the question "who spoken when", most of relevant applications in reality are more interested in determining "who spoken what". Whether it is the conventional modularized approach or the…

Streaming end-to-end multi-talker speech recognition aims at transcribing the overlapped speech from conversations or meetings with an all-neural model in a streaming fashion, which is fundamentally different from a modular-based approach…

The recent text-to-speech (TTS) has achieved quality comparable to that of humans; however, its application in spoken dialogue has not been widely studied. This study aims to realize a TTS that closely resembles human dialogue. First, we…

Transformer-based models have demonstrated their effectiveness in automatic speech recognition (ASR) tasks and even shown superior performance over the conventional hybrid framework. The main idea of Transformers is to capture the…

As speech-enabled devices such as smartphones and smart speakers become increasingly ubiquitous, there is growing interest in building automatic speech recognition (ASR) systems that can run directly on-device; end-to-end (E2E) speech…

This paper has two goals. First, we present the turn-taking annotation layers created for 95 minutes of conversational speech of the Graz Corpus of Read and Spontaneous Speech (GRASS), available to the scientific community. Second, we…

Stuttering affects approximately 1% of the global population, impacting communication and quality of life. While recent advances in deep learning have pushed the boundaries of automatic speech dysfluency detection, rule-based approaches…

Dysarthria is a speech disorder that hinders communication due to difficulties in articulating words. Detection of dysarthria is important for several reasons as it can be used to develop a treatment plan and help improve a person's quality…

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…

End-to-end (E2E) models have shown to outperform state-of-the-art conventional models for streaming speech recognition [1] across many dimensions, including quality (as measured by word error rate (WER)) and endpointer latency [2]. However,…

Disfluency, though originating from human spoken utterances, is primarily studied as a uni-modal text-based Natural Language Processing (NLP) task. Based on early-fusion and self-attention-based multimodal interaction between text and…

Multilingual end-to-end (E2E) models have shown great promise in expansion of automatic speech recognition (ASR) coverage of the world's languages. They have shown improvement over monolingual systems, and have simplified training and…