Walrus Technical Report
eess.AS, cs.CL
Submitted: 2026-11-10
Updated: 2026-11-10
Code: https://github.com/sony-speech/walrus
Terminology
Sources
- Phi-4-Mini Technical Report: Compact yet Powerful Multimodal Language Models via Mixture-of-LoRAs
- Seamless: Multilingual Expressive and Streaming Speech Translation
- LibriMix: An Open-Source Dataset for Generalizable Speech Separation
- FMA: A Dataset For Music Analysis
- Kimi-Audio Technical Report
- AISHELL-4: An Open Source Dataset for Speech Enhancement, Separation, Recognition and Speaker Diarization in Conference Scenario
- Kraken: LLM-based Speech-to-Speech Translation via Low-bitrate VQ and Dual-path Source Conditioning
- Conformer: Convolution-augmented Transformer for Speech Recognition
- GPT-4o System Card
- WavChat: A Survey of Spoken Dialogue Models
- Benchmarking Speech-to-Speech Translation Models
- DeepDialogue: A Multi-Turn Emotionally-Rich Spoken Dialogue Dataset
- TAC: Timestamped Audio Captioning
- MECAT: A Multi-Experts Constructed Benchmark for Fine-Grained Audio Understanding Tasks
- VIBEVOICE-ASR Technical Report
- MLS: A Large-Scale Multilingual Dataset for Speech Research
- SpeechBrain: A General-Purpose Speech Toolkit
- Qwen3-ASR Technical Report
- AISHELL-3: A Multi-speaker Mandarin TTS Corpus and the Baselines
- Vocos: Closing the gap between time-domain and Fourier-based neural vocoders for high-quality audio synthesis
Related papers
- WavCube: Unifying Speech Representation for Understanding and Generation via Semantic-Acoustic Joint Modeling
- From perception to production: how acoustic invariance facilitates articulatory learning in a self-supervised vocal imitation model
- Read What You Hear: Reference-Free Hypotheses Evaluation with Acoustic Discrepancy
- pyFDN: A Python Toolbox for Feedback Delay Network Design, Analysis, and Optimization
- GigaSpeechBench: A Real-World Multilingual Speech-to-Text Benchmark
- DM-ASR: Diarization-aware Multi-speaker ASR with Unified Offline and Online Decoding with Large Language Models