Towards Fine-Grained Multi-Dimensional Speech Understanding: Data Pipeline, Benchmark, and Model
☆39May 21, 2026Updated 6 months ago
Alternatives and similar repositories for FMSU-Bench
Users that are interested in FMSU-Bench are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- ☆13Mar 25, 2026Updated 7 months ago
- This challenge focuses on evaluating speech recognition and semantic understanding capabilities of AI glasses in complex real-world envir…☆18Aug 22, 2026Updated 3 months ago
- An Open-Source Multidimension Speech Understanding Foundation Model Built upon OpenPangu on Ascend NPUs☆41Mar 15, 2026Updated 8 months ago
- ☆22Jun 26, 2026Updated 4 months ago
- Demo page of MINT-Bench☆13Nov 10, 2026Updated last week
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- ☆16Sep 28, 2026Updated last month
- ☆41May 19, 2026Updated 6 months ago
- ☆27Jun 16, 2026Updated 5 months ago
- ☆54Oct 20, 2026Updated last month
- ☆21Dec 14, 2025Updated 11 months ago
- ☆10May 28, 2026Updated 5 months ago
- ☆20Aug 11, 2026Updated 3 months ago
- Open repository of "MSU-Bench: Towards Understanding the Conversational Multi-Speaker Scenarios"☆39Jul 7, 2026Updated 4 months ago
- ☆61May 2, 2026Updated 6 months ago
- GPUs on demand by Runpod - Special Offer Available • AdRun AI, ML, and HPC workloads on powerful cloud GPUs—without limits or wasted spend. Deploy GPUs in under a minute and pay by the second.
- Speaker-Reasoner: Scaling Interaction Turns and Reasoning Patterns for Timestamped Speaker-Attributed ASR☆104May 13, 2026Updated 6 months ago
- OmniCodec: Low Frame Rate Universal Audio Codec with Semantic–Acoustic Disentanglement☆60Apr 17, 2026Updated 7 months ago
- ☆18Jul 28, 2026Updated 3 months ago
- Llasa Speed Up☆71Jan 18, 2026Updated 10 months ago
- ☆30Sep 9, 2026Updated 2 months ago
- M5-TTS is a lightweight 50M-parameter TTS language model supporting real-time CPU inference, multilingual and multi-dialect synthesis, ze…☆110Nov 12, 2026Updated last week
- Fast Streaming TTS with MTP Acceleration and X-pred Mean Flow Distillation☆91Jun 16, 2026Updated 5 months ago
- Open-Source Turn-Taking Detection Model and Dataset for Full-Duplex Spoken Dialogue Systems☆166Jan 25, 2026Updated 9 months ago
- SphereVAE: Hyperspherical Latent Autoencoders for Robust Autoregressive Speech Representation Modeling☆27Sep 11, 2026Updated 2 months ago
- Virtual machines for every use case on DigitalOcean • AdGet dependable uptime with 99.99% SLA, simple security tools, and predictable monthly pricing with DigitalOcean's virtual machines, called Droplets.
- DRAMA-Eval is a comprehensive bilingual (English & Chinese) benchmark designed to evaluate context-aware, multi-turn, and multi-speaker s…☆67Nov 14, 2026Updated last week
- ICASSP2026 HumDial Challenge☆65May 28, 2026Updated 5 months ago
- We propose C2SER, a novel audio-language model designed to enhance the stability and accuracy of speech emotion recognition through conte…☆21Mar 3, 2025Updated last year
- The Full-Duplex Interaction Track of the ICASSP 2026 Human-like Spoken Dialogue Systems Challenge aims to advance the evaluation of full-…☆52Apr 27, 2026Updated 6 months ago
- SemBridge: Semantic Token Anchoring for Continuous-Latent Autoregressive Speech Generation☆107Nov 5, 2026Updated 2 weeks ago
- ☆96Oct 14, 2026Updated last month
- Reward models for TTS post-training, evaluating multiple dimensions of speech quality, including naturalness, expressiveness, and other p…☆22Nov 12, 2026Updated last week
- Official repository of the paper "On-Policy Self-Distillation for Multi-Dialect ASR: Mastering Dialects, Retaining Mandarin".☆117Sep 4, 2026Updated 2 months ago
- An instruct text-to-speech solution based on LLaSA and CosyVoice2 developed by the ASLP lab and collaborators.☆267Feb 26, 2026Updated 8 months ago
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- ☆49Nov 13, 2026Updated last week
- ☆81Updated this week
- LLaSE-G1: Incentivizing Generalization Capability for LLaMA-based Speech Enhancement☆52Mar 10, 2025Updated last year
- A Robust Low-Latency Streaming Zero-Shot Voice Conversion☆208Sep 13, 2026Updated 2 months ago
- A Large-scale Wu Dialect Speech Corpus with Multi-dimensional Annotations☆204Feb 6, 2026Updated 9 months ago
- YingMusic-Singer-Plus: Controllable Singing Voice Synthesis with Flexible Lyric Manipulation and Annotation-free Melody Guidance☆148Apr 12, 2026Updated 7 months ago
- A Music Semantic VAE for music understanding, generation, and high-fidelity reconstruction.☆229Oct 27, 2026Updated 3 weeks ago
Are these results useful?