Speech-to-speech Translation between Untranscribed Unknown Languages
In this paper, we explore a method for training speech-to-speech translation tasks without any transcription or linguistic supervision. Our proposed method consists of two steps: First, we train and generate discrete representation with unsupervised term discovery with a discrete quantized autoencoder. Second, we train a sequence-to-sequence model that directly maps the source language speech to the target language's discrete representation. Our proposed method can directly generate target speech without any auxiliary or pre-training steps with a source or target transcription. To the best of our knowledge, this is the first work that performed pure speech-to-speech translation between untranscribed unknown languages.
Code (0)
등록된 구현이 없습니다.
Tasks
Speech-to-Speech TranslationTranslationSimilar Papers 제목 키워드 기반
Spoken Term Discovery for Language Documentation using Translations
Vast amounts of speech data collected for language documentation and research remain untranscribed and unsearchable, but often a small amount of speech may have text translations available. We present a method for partia…
TranslationAdaSpeech 2: Adaptive Text to Speech with Untranscribed Data
Text to speech (TTS) is widely used to synthesize personal voice for a target speaker, where a well-trained source TTS model is fine-tuned with few paired adaptation data (speech and its transcripts) on this target speak…
Decodertext-to-speechText to SpeechGuided-TTS:Text-to-Speech with Untranscribed Speech
Most neural text-to-speech (TTS) models require $\langle$speech, transcript$\rangle$ paired data from the desired speaker for high-quality speech synthesis, which limits the usage of large amounts of untranscribed data f…
Speech Synthesistext-to-speechText to SpeechText-To-Speech SynthesisGuided-TTS 2: A Diffusion Model for High-quality Adaptive Text-to-Speech with Untranscribed Data
We propose Guided-TTS 2, a diffusion-based generative model for high-quality adaptive TTS using untranscribed data. Guided-TTS 2 combines a speaker-conditional diffusion model with a speaker-dependent phoneme classifier …
text-to-speechText to SpeechLow Resource German ASR with Untranscribed Data Spoken by Non-native Children -- INTERSPEECH 2021 Shared Task SPAPL System
This paper describes the SPAPL system for the INTERSPEECH 2021 Challenge: Shared Task on Automatic Speech Recognition for Non-Native Children's Speech in German. ~ 5 hours of transcribed data and ~ 60 hours of untranscri…
Acoustic ModellingAutomatic Speech RecognitionAutomatic Speech Recognition (ASR)Data Augmentation+3