Related papers: Discourse-Aware Dual-Track Streaming Response for …

Multi-speaker automatic speech recognition (ASR) aims to transcribe conversational speech involving multiple speakers, requiring the model to capture not only what was said, but also who said it and sometimes when it was spoken. Recent…

Full-duplex spoken dialogue requires a model to keep listening while generating its own spoken response. This is challenging for large language models (LLMs), which are designed to extend a single coherent sequence and do not naturally…

We introduce Delayed Streams Modeling (DSM), a flexible formulation for streaming, multimodal sequence-to-sequence learning. Sequence-to-sequence generation is often cast in an offline manner, where the model consumes the complete input…

End-to-end speech-in speech-out dialogue systems are emerging as a powerful alternative to traditional ASR-LLM-TTS pipelines, generating more natural, expressive responses with significantly lower latency. However, these systems remain…

Most end-to-end (E2E) spoken dialogue systems (SDS) rely on voice activity detection (VAD) for turn-taking, but VAD fails to distinguish between pauses and turn completions. Duplex SDS models address this by predicting output continuously,…

Multimodal language models that process both text and speech have a potential for applications in spoken dialogue systems. However, current models face two major challenges in response generation latency: (1) generating a spoken response…

Typical high quality text-to-speech (TTS) systems today use a two-stage architecture, with a spectrum model stage that generates spectral frames and a vocoder stage that generates the actual audio. High-quality spectrum models usually…

Streaming recognition of multi-talker conversations has so far been evaluated only for 2-speaker single-turn sessions. In this paper, we investigate it for multi-turn meetings containing multiple speakers using the Streaming Unmixing and…

Full-duplex spoken dialogue systems (FDSDS) enable more natural human-machine interactions by allowing real-time user interruptions and backchanneling, compared to traditional SDS that rely on turn-taking. However, existing benchmarks lack…

Most research on task oriented dialog modeling is based on written text input. However, users interact with practical dialog systems often using speech as input. Typically, systems convert speech into text using an Automatic Speech…

Text-to-Speech (TTS) models have advanced significantly, aiming to accurately replicate human speech's diversity, including unique speaker identities and linguistic nuances. Despite these advancements, achieving an optimal balance between…

Although the deep integration of the Automatic Speech Recognition (ASR) system with Large Language Models (LLMs) has significantly improved accuracy, the deployment of such systems in low-latency streaming scenarios remains challenging. In…

Dysarthric speech reconstruction (DSR) aims to convert dysarthric speech into comprehensible speech while maintaining the speaker's identity. Despite significant advancements, existing methods often struggle with low speech intelligibility…

This paper summarizes our submission to Task 2 of the second track of the 10th Dialog System Technology Challenge (DSTC10) "Knowledge-grounded Task-oriented Dialogue Modeling on Spoken Conversations". Similar to the previous year's…

Streaming voice conversion has become increasingly popular for its potential in real-time applications. The recently proposed DualVC 2 has achieved robust and high-quality streaming voice conversion with a latency of about 180ms.…

The task of joint dialog sentiment classification (DSC) and act recognition (DAR) aims to simultaneously predict the sentiment label and act label for each utterance in a dialog. In this paper, we put forward a new framework which models…

During conversational interactions, humans subconsciously engage in concurrent thinking while listening to a speaker. Although this internal cognitive processing may not always manifest as explicit linguistic structures, it is instrumental…

While modern Text-to-Speech (TTS) systems achieve high fidelity for read-style speech, they struggle to generate Autonomous Sensory Meridian Response (ASMR), a specialized, low-intensity speech style essential for relaxation. The inherent…

The Speaker Diarization and Recognition (SDR) task aims to predict "who spoke when and what" within an audio clip, which is a crucial task in various real-world multi-speaker scenarios such as meeting transcription and dialogue systems.…

Current speech language models generate responses directly without explicit reasoning, leading to errors that cannot be corrected once audio is produced. We introduce \textbf{``Silent Thought, Spoken Answer''} -- a paradigm where speech…