paper-with-me

홈 › Papers

Improving Joint Speech-Text Representations Without Alignment

2023-08-11 · Cal Peyser, Zhong Meng, Ke Hu, Rohit Prabhavalkar, Andrew Rosenberg, Tara N. Sainath, Michael Picheny, Kyunghyun Cho

The last year has seen astonishing progress in text-prompted image generation premised on the idea of a cross-modal representation space in which the text and image domains are represented jointly. In ASR, this idea has found application as joint speech-text encoders that can scale to the capacities of very large parameter models by being trained on both unpaired speech and text. While these methods show promise, they have required special treatment of the sequence-length mismatch inherent in speech and text, either by up-sampling heuristics or an explicit alignment model. In this work, we offer evidence that joint speech-text encoders naturally achieve consistent representations across modalities by disregarding sequence length, and argue that consistency losses could forgive length differences and simply assume the best alignment. We show that such a loss improves downstream WER in both a large-parameter monolingual and multilingual system.

📄 PDF Abstract BibTeX arXiv:2308.06125

Code (0)

등록된 구현이 없습니다.

Tasks

Speech Recognition

Similar Papers 제목 키워드 기반

OmniDRCA: Parallel Speech-Text Foundation Model via Dual-Resolution Speech Representations and Contrastive Alignment

2025-06-11 · Chao-Hong Tan, Qian Chen, Wen Wang, Chong Deng 외

Recent studies on end-to-end speech generation with large language models (LLMs) have attracted significant community attention, with multiple works extending text-based LLMs to generate discrete speech tokens. Existing …

cross-modal alignmentQuestion AnsweringSpeech SynthesisText Generation

mSLAM: Massively multilingual joint pre-training for speech and text

2022-02-03 · Ankur Bapna, Colin Cherry, Yu Zhang, Ye Jia 외

We present mSLAM, a multilingual Speech and LAnguage Model that learns cross-lingual cross-modal representations of speech and text by pre-training jointly on large amounts of unlabeled speech and text in multiple langua…

cross-modal alignmentintent-classificationIntent ClassificationLanguage Modeling+4

Shared Latent Representation for Joint Text-to-Audio-Visual Synthesis

2025-11-07 · Dogucan Yaman, Seymanur Akti, Fevziye Irem Eyiokur, Alexander Waibel arxiv

We propose a text-to-talking-face synthesis framework leveraging latent speech representations from HierSpeech++. A Text-to-Vec module generates Wav2Vec2 embeddings from text, which jointly condition speech and face gene…

Adaptive Inner Speech-Text Alignment for LLM-based Speech Translation

2025-03-13 · Henglyu Liu, Andong Chen, Kehai Chen, Xuefeng Bai 외

Recent advancement of large language models (LLMs) has led to significant breakthroughs across various tasks, laying the foundation for the development of LLM-based speech translation systems. Existing methods primarily …

Cross-Modal RetrievalTranslation

JDI-T: Jointly trained Duration Informed Transformer for Text-To-Speech without Explicit Alignment

2020-05-15 · Dan Lim, Won Jang, Gyeonghwan O, Heayoung Park 외

We propose Jointly trained Duration Informed Transformer (JDI-T), a feed-forward Transformer with a duration predictor jointly trained without explicit alignments in order to generate an acoustic feature sequence from an…

text-to-speechText to Speech