Speech Processing

December 1, 2023
Unsupervised speech-to-speech translation from monolingual data
- Machine Translation ·
- Product ·
- Speech Processing
October 26, 2023
Spoken question answering and speech continuation using a spectrogram-powered LLM
- Natural Language Processing ·
- Speech Processing
October 19, 2023
English learners can now practice speaking on Search
- Education Innovation ·
- Product ·
- Speech Processing
June 22, 2023
SoundStorm: Efficient parallel audio generation
- Sound & Accoustics ·
- Speech Processing
June 21, 2023
Responsible AI at Google Research: AI for Social Good
- Human-Computer Interaction and Visualization ·
- RAI-HCT Highlights ·
- Speech Processing
June 7, 2023
Evaluating speech synthesis in many languages with SQuId
- Conferences & Events ·
- Speech Processing
June 2, 2023
AVFormer: Injecting vision into frozen speech models for zero-shot AV-ASR
- Machine Intelligence ·
- Speech Processing
March 6, 2023
Universal Speech Model (USM): State-of-the-art speech AI for 100+ languages
- Speech Processing
December 14, 2022
Who said what? Recorder's on-device solution for labeling speakers
- Mobile Systems ·
- Sound & Accoustics ·
- Speech Processing
September 18, 2022
Google at Interspeech 2022
- Conferences & Events ·
- Speech Processing
June 30, 2022
Identifying Disfluencies in Natural Speech
- Conferences & Events ·
- Machine Intelligence ·
- Speech Processing
April 1, 2022
Introducing CVSS: A Massively Multilingual Speech-to-Speech Translation Corpus
- Machine Translation ·
- Open Source Models & Datasets ·
- Speech Processing