Speech

语音基础理论、应用

S

S Speech

[浏览需要 0 积分] 发布于2025-03-07 09:36:31

【CP-力作鼎推】OWLS: Scaling Laws for Multilingual Speech Recognition and Translation Models
论文链接 Neural scaling laws offer valuable insights for designing robust sequence processing architectures. While these laws have b...

赞 2

评论 1

浏览 335

语音
S

S Speech

[浏览需要 0 积分] 发布于2025-03-06 06:10:10

【CP】Unveiling the Potential of LLM-Based ASR on Chinese Open-Source Datasets
论文链接代码链接

赞 2

评论 1

浏览 305

语音
S

S Speech

[浏览需要 0 积分] 发布于2025-03-05 08:10:22

【CP】Audio-CoT: Exploring Chain-of-Thought Reasoning in Large Audio Language Model
论文链接

赞 2

评论

浏览 342

语音
S

S Speech

[浏览需要 0 积分] 发布于2025-03-04 06:34:20

【优秀博士生】Jinchuan Tian—CMU
学术链接 Git 链接

赞 2

评论

浏览 308

语音
S

S Speech

[浏览需要 0 积分] 发布于2025-02-27 02:19:11

【JP】High fidelity zero shot speaker adaptation in text to speech synthesis with denoising diffusion GAN
论文链接

赞 2

评论

浏览 338

语音
S

S Speech

[浏览需要 0 积分] 发布于2025-02-21 09:50:45

【资源】AudioLLM / SpeechLLM方向论文、代码、数据汇总GIT
论文链接

赞 2

评论

浏览 433

语音
S

S Speech

[浏览需要 0 积分] 发布于2025-02-21 09:11:48

【JP】A speech recognition method with enhanced transformer decoder
论文链接

赞 2

评论

浏览 400

语音
S

S Speech

[浏览需要 0 积分] 发布于2025-02-21 05:27:08

【TR】OSUM: Advancing Open Speech Understanding Models with Limited Resources in Academia
论文链接代码链接 Large Language Models (LLMs) have made significant progress in various downstream tasks, inspiring the development of ...

赞 3

评论

浏览 474

语音
S

S Speech

[浏览需要 0 积分] 发布于2025-02-17 06:29:24

【CP】End-to-End Speech Recognition with Pre-trained Masked Language Model
论文链接 We present a novel approach to end-to-end automatic speech recognition (ASR) that utilizes pre-trained masked language mode...

赞 2

评论 1

浏览 493

语音
S

S Speech

[浏览需要 0 积分] 发布于2025-02-11 03:27:05

【CP】RFWAVE: MULTI-BAND RECTIFIED FLOW FOR AUDIO WAVEFORM RECONSTRUCTION
论文链接代码链接

赞 2

评论

浏览 402

语音
S

S Speech

[浏览需要 0 积分] 发布于2025-02-07 11:17:38

【Code】k2 官方提供AudioLLM配方，复现Qwen-Audio
代码链接

赞 3

评论

浏览 485

语音
S

S Speech

[浏览需要 0 积分] 发布于2025-02-07 09:23:54

【CP】ADVANCING MULTI-TALKER ASR PERFORMANCE WITH LARGE LANGUAGE MODELS
论文链接模型结构训练策略

赞 2

评论

浏览 469

语音
S

S Speech

[浏览需要 0 积分] 发布于2025-02-07 03:27:40

【CP】Speech Data Selection for Efficient ASR Fine-Tuning using Domain Classifier and Pseudo-Label Filtering
论文链接

赞 2

评论

浏览 539

语音
S

S Speech

[浏览需要 0 积分] 发布于2025-02-06 11:15:14

【CP】Optimized Self-supervised Training with BEST-RQ for Speech Recognition
论文链接

赞 2

评论

浏览 481

语音
S

S Speech

[浏览需要 0 积分] 发布于2025-02-05 03:33:08

【TR】FireRedASR: Open-Source Industrial-Grade Mandarin Speech Recognition Models from Encoder-Decoder to LLM Integration
论文链接

赞 2

评论

浏览 474

语音
S

S Speech

[浏览需要 0 积分] 发布于2025-01-23 03:35:37

【CP】TTS-Transducer: End-to-End Speech Synthesis with Neural Transducer
论文链接官网链接

赞 2

评论

浏览 611

语音
S

S Speech

[浏览需要 0 积分] 发布于2025-01-22 06:53:18

【CP】E2 TTS: EMBARRASSINGLY EASY FULLY NON-AUTOREGRESSIVE ZERO-SHOT TTS
论文链接 LJ Speech 数据链接 am 代码链接 1 am 代码链接 2 vocoder 代码链接网站链接

赞 2

评论

浏览 757

语音
S

S Speech

[浏览需要 0 积分] 发布于2025-01-22 03:34:56

【访谈】小米语音首席科学家 Daniel Povey：语音识别卷完了，下一个机会在哪里？| 智者访谈
Povey 观点链接

赞 2

评论

浏览 638

语音
S

S Speech

[浏览需要 0 积分] 发布于2025-01-20 11:26:23

【CP】F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching
论文链接代码链接

赞 2

评论

浏览 529

语音
S

S Speech

[浏览需要 0 积分] 发布于2025-01-17 07:43:22

《细水长flow之TARFLOW：流模型满血归来？》
https://kexue.fm/archives/10667 Normalizing Flow 的生成效果也赶上了 SOTA。

赞 2

评论

浏览 652

文本