ASLP-lab Claim this profile

Di♪♪Rhythm: Blazingly Fast and Embarrassingly Simple End-to-End Full-Length Song Generation with Latent Diffusion

OSUM & OSUM-EChat, open speech understanding model and empathetic spoken chatbot based on it, open-sourced by ASLP@NPU.

A Large-scale Cantonese Speech Corpus with Multi-dimensional Annotation

A song aesthetic evaluation toolkit trained on SongEval.

A Lightweight and Streaming Zero-Shot Voice Conversion via Mean Flows

An instruct text-to-speech solution based on LLaSA and CosyVoice2 developed by the ASLP lab and collaborators.

Official repository for the WenetSpeech-Chuan dataset.

A Large-scale Wu Dialect Speech Corpus with Multi-dimensional Annotations

Di♪♪Rhythm 2: Efficient And High Fidelity Song Generation Via Block Flow Matching

No description.

Open-Source Turn-Taking Detection Model and Dataset for Full-Duplex Spoken Dialogue Systems

Speaker-Reasoner: Scaling Interaction Turns and Reasoning Patterns for Timestamped Speaker-Attributed ASR

Official code of SenSE.

YingMusic-Singer-Plus: Controllable Singing Voice Synthesis with Flexible Lyric Manipulation and Annotation-free Melody Guidance

Fast Streaming TTS with MTP Acceleration and X-pred Mean Flow Distillation

Llasa Speed Up

ICASSP2026 HumDial Challenge

No description.

LLaSE-G1: Incentivizing Generalization Capability for LLaMA-based Speech Enhancement

OmniCodec: Low Frame Rate Universal Audio Codec with Semantic–Acoustic Disentanglement

The Full-Duplex Interaction Track of the ICASSP 2026 Human-like Spoken Dialogue Systems Challenge aims to advance the evaluation of full-duplex dialogue systems by in- troducing a dual-channel dialogue dataset of real human- recorded conversations.

No description.

An Open-Source Multidimension Speech Understanding Foundation Model Built upon OpenPangu on Ascend NPUs

No description.

No description.

Towards Fine-Grained Multi-Dimensional Speech Understanding: Data Pipeline, Benchmark, and Model

Open repository of "MSU-Bench: Towards Understanding the Conversational Multi-Speaker Scenarios"

M7-TTS: A Mini-Scale Multilingual and Multi-Dialect Text-to-Speech Language Model with Mimi codec and Multi Token Prediction

No description.

No description.

This challenge focuses on evaluating speech recognition and semantic understanding capabilities of AI glasses in complex real-world environments.

We propose C2SER, a novel audio-language model designed to enhance the stability and accuracy of speech emotion recognition through contextual perception and chain of Thought (CoT).

No description.

No description.

No description.

Demo page of MINT-Bench

No description.

No description.

SoulX-Podcast is an inference codebase by the Soul AI team for generating high-fidelity podcasts from text.

No description.

GenSE: Generative Speech Enhancement via Language Models using Hierarchical Modeling

No description.

No description.

No description.

No description.

demopages of flashtts

OSUM-EChat demo page

The project is associated with the recently-launched INTERSPEECH 2025 Workshop on Multilingual Conversational Speech Language Model (MLC-SLM) to provide participants with baseline systems for speech recognition and speaker diarization in multilingual conversational scenario.

No description.

Online demo page for "MSU-Bench: Towards Understanding the Conversational Multi-Speaker Scenarios"

No description.