Sep 2026· Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence· 0 citations· 7 references
TL;DR
DeepL Voice achieves competitive transcription quality through proprietary real-time ASR models and eliminates translation "flickering" via stable text streaming while maintaining low latency.
Abstract
DeepL Voice is a real-time speech-to-speech translation system for global business communication, following a pragmatic incremental approach: developing a production-grade cascaded speech-to-speech-translation (S2ST) system, while exploring end-to-end solutions in parallel.
The production system (launched November 2024) achieves competitive transcription quality through proprietary real-time ASR models and eliminates translation "flickering" via stable text streaming while maintaining low latency.
Supporting 18 input languages and 30+ target languages, it offers DeepL Voice for Meetings (Microsoft Teams/Zoom integration), DeepL Voice for Conversations (mobile apps), as well as the DeepL API for Voice.
Key features include customizable formality and glossary support for business-appropriate communication, with voice cloning TTS under development.
VoiceChat-TTS is proposed, a low-latency, continuous, and streamable text-to-speech model for interactive agents that enables always-on, responsive speech generation while preserving modularity and high speech quality.
Edresson Casanova, Jaehyeon Kim, Mariana Graterol Fuenmayor et al.· 3 citations
The resulting 82M-parameter model, Wayu-Paxa-TTS-Edge, enables on-device Thai TTS without reference audio and achieves the lowest pause-placement error and intra-word pause rates among the three systems.
Kunat Pipatanakul, Potsawee Manakul, Warit Sirichotedumrong et al.· 1 citation
The rapid expansion of online IT education has created a pressing need to bridge the English-Vietnamese language barrier for non-native learners, as subtitle-based solutions impose cognitive load and fail to preserve the lecturer’s vocal identity. This paper presents a cascade Speech-to-Speech Translation (S2ST) pipeli...
Trang Thi Thuy Pham, Nhut Minh Nguyen, T. Nguyen· International Conference on...· 0 citations
This work proposes an efficient method to add streaming ASR capabilities to an existing duplex S2S model by introducing a lightweight ASR head in parallel to the agent text head, enabling real-time user transcription while preserving full-duplex conversational capabilities including turn-taking and barge-in handling.
Ke Hu, Nourchene Ferchichi, Edresson Casanova et al.· 1 citation
The results demonstrate that full-duplex interaction, speech recognition and generation, general language capabilities, and external tool use can be integrated in a single open speech-to-speech model without sacrificing real-time conversational behavior.
Jagadeesh Balam, Travis M. Bartley, Edresson Casanova et al.· 2 citations· ⚡1
Speech language models (speech LLMs) can generate plausible outputs from audio that contains no usable speech evidence. We study this failure as a pre-generation support-estimation problem and present SURE-Voice, a training-free front end that decides whether an audio prompt contains intelligible speech evidence before...
Mengzhe Geng· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
