Google's Speech AI AudioPaLM Performs Translation with Voice Transfer

Researchers at Google announced AudioPaLM, a large language model (LLM) that performs text-to-speech (TTS), automated speech recognition (ASR), and speech-to-speech translation (S2ST) with voice transfer. AudioPaLM is based on the PaLM-2 LLM and outperforms OpenAI's Whisper on translation benchmarks.

ai anthony asr automated automated speech recognition benchmarks google language language model large language large language model large language models llm ml & data engineering natural language processing openai palm recognition researchers s2st speech speech ai speech recognition speech-to-speech translation text text-to-speech transfer translation tts voice whisper