SeamlessM4T-Massively Multilingual & Multimodal Machine Translation
What does it take to create the Babel Fish, a tool that can help individuals translate speech
between any two languages? While recent breakthroughs in text-based models have …
between any two languages? While recent breakthroughs in text-based models have …
Seamless: Multilingual Expressive and Streaming Speech Translation
Large-scale automatic speech translation systems today lack key features that help machine-
mediated communication feel seamless when compared to human-to-human dialogue. In …
mediated communication feel seamless when compared to human-to-human dialogue. In …
Multilingual large language model: A survey of resources, taxonomy and frontiers
Multilingual Large Language Models are capable of using powerful Large Language
Models to handle and respond to queries in multiple languages, which achieves remarkable …
Models to handle and respond to queries in multiple languages, which achieves remarkable …
Multi-resolution HuBERT: Multi-resolution speech self-supervised learning with masked unit prediction
Existing Self-Supervised Learning (SSL) models for speech typically process speech signals
at a fixed resolution of 20 milliseconds. This approach overlooks the varying informational …
at a fixed resolution of 20 milliseconds. This approach overlooks the varying informational …
Salm: Speech-augmented language model with in-context learning for speech recognition and translation
We present a novel Speech Augmented Language Model (SALM) with multitask and in-
context learning capabilities. SALM comprises a frozen text LLM, a audio encoder, a …
context learning capabilities. SALM comprises a frozen text LLM, a audio encoder, a …
Evaluating multilingual speech translation under realistic conditions with resegmentation and terminology
We present the ACL 60/60 evaluation sets for multilingual translation of ACL 2022 technical
presentations into 10 target languages. This dataset enables further research into …
presentations into 10 target languages. This dataset enables further research into …
QUESPA Submission for the IWSLT 2024 Dialectal and Low-resource Speech Translation Task
This article describes the QUESPA team speech translation (ST) submissions for the
Quechua to Spanish (QUE–SPA) track featured in the Evaluation Campaign of IWSLT 2024 …
Quechua to Spanish (QUE–SPA) track featured in the Evaluation Campaign of IWSLT 2024 …
Evaluating self-supervised speech representations for indigenous American languages
The application of self-supervision to speech representation learning has garnered
significant interest in recent years, due to its scalability to large amounts of unlabeled data …
significant interest in recent years, due to its scalability to large amounts of unlabeled data …
NAVER LABS Europe's Multilingual Speech Translation Systems for the IWSLT 2023 Low-Resource Track
This paper presents NAVER LABS Europe's systems for Tamasheq-French and Quechua-
Spanish speech translation in the IWSLT 2023 Low-Resource track. Our work attempts to …
Spanish speech translation in the IWSLT 2023 Low-Resource track. Our work attempts to …
PolyVoice: Language Models for Speech to Speech Translation
With the huge success of GPT models in natural language processing, there is a growing
interest in applying language modeling approaches to speech tasks. Currently, the dominant …
interest in applying language modeling approaches to speech tasks. Currently, the dominant …