From TOWER to SPIRE: Adding the Speech Modality to a Translation-Specialist LLM

• URL: http://arxiv.org/abs/2503.10620v3
• Date: Wed, 22 Oct 2025 08:47:03 GMT
• Title: From TOWER to SPIRE: Adding the Speech Modality to a Translation-Specialist LLM
• Authors: Kshitij Ambilduke, Ben Peters, Sonal Sannigrahi, Anil Keshwani, Tsz Kin Lam, Bruno Martins, André F. T. Martins, Marcely Zanon Boito,
• Abstract summary: We introduce Spire, a speech-augmented language model (LM) capable of both translating and transcribing speech input from English into 10 other languages.<n>Spire integrates the speech modality into an existing multilingual LM via speech discretization and continued pre-training using only 42.5K hours of speech.
• Score: 24.31773681590982
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We introduce Spire, a speech-augmented language model (LM) capable of both translating and transcribing speech input from English into 10 other languages as well as translating text input in both language directions. Spire integrates the speech modality into an existing multilingual LM via speech discretization and continued pre-training using only 42.5K hours of speech. In particular, we adopt the pretraining framework of multilingual LMs and treat discretized speech input as an additional translation language. This approach not only equips the model with speech capabilities, but also preserves its strong text-based performance. We achieve this using significantly less data than existing speech LMs, demonstrating that discretized speech input integration as an additional language is feasible during LM adaptation. We make our code and models available to the community.

Related papers

• Speech Language Models for Under-Represented Languages: Insights from Wolof [9.14632796153174]
  We present our journey in training a speech language model for Wolof, an underrepresented language spoken in West Africa.<n>We first emphasize the importance of collecting large-scale, spontaneous, high-quality unsupervised speech data.<n>We show that continued pretraining HuBERT on this dataset outperforms both the base model and African-centric models on ASR.
  arXiv  Detail & Related papers  (2025-09-18T19:01:48Z)
• ProsodyLM: Uncovering the Emerging Prosody Processing Capabilities in Speech Language Models [70.56468982313834]
  We propose ProsodyLM, which introduces a simple tokenization scheme amenable to learning prosody.<n>We find that ProsodyLM can learn surprisingly diverse emerging prosody processing capabilities through pre-training alone.
  arXiv  Detail & Related papers  (2025-07-27T00:59:01Z)
• SparQLe: Speech Queries to Text Translation Through LLMs [0.8901073744693314]
  This study introduces a novel approach that leverages self-supervised speech representations in combination with instruction-tuned LLMs for speech-to-text translation. Our experiments demonstrate that this method effectively preserves the semantic content of the input speech and serves as an effective bridge between self-supervised speech models and instruction-tuned LLMs.
  arXiv  Detail & Related papers  (2025-02-13T12:57:15Z)
• Zero-resource Speech Translation and Recognition with LLMs [38.11535502039386]
  We propose to leverage a multilingual Large Language Model (LLM) to perform ST and ASR in languages for which the model has never seen paired audio-text data.<n>We achieve this by using a pre-trained multilingual speech encoder, a multilingual LLM, and a lightweight adaptation module that maps the audio representations to the token embedding space of the LLM.
  arXiv  Detail & Related papers  (2024-12-24T17:37:11Z)
• DeSTA2: Developing Instruction-Following Speech Language Model Without Speech Instruction-Tuning Data [84.01401439030265]
  Recent end-to-end speech language models (SLMs) have expanded upon the capabilities of large language models (LLMs)<n>We present a simple yet effective automatic process for creating speech-text pair data.<n>Our model demonstrates general capabilities for speech-related tasks without the need for speech instruction-tuning data.
  arXiv  Detail & Related papers  (2024-09-30T07:01:21Z)
• Enhancing Multilingual Speech Generation and Recognition Abilities in LLMs with Constructed Code-switched Data [30.966072545451183]
  We propose a MutltiLingual MultiTask (MLMT) model, integrating multilingual speech generation and recognition tasks within the single LLM. We develop an effective data construction approach that splits and equips words from different languages to equip synthesiss with CS ability without relying on CS data.
  arXiv  Detail & Related papers  (2024-09-17T08:11:07Z)
• Large Language Model Can Transcribe Speech in Multi-Talker Scenarios with Versatile Instructions [68.98811048970963]
  We present a pioneering effort to investigate the capability of large language models (LLMs) in transcribing speech in multi-talker environments. Our approach utilizes WavLM and Whisper encoder to extract multi-faceted speech representations that are sensitive to speaker characteristics and semantic context. Comprehensive experiments reveal the promising performance of our proposed system, MT-LLM, in cocktail party scenarios.
  arXiv  Detail & Related papers  (2024-09-13T07:28:28Z)
• SpeechPrompt: Prompting Speech Language Models for Speech Processing Tasks [94.10497337235083]
  We are first to explore the potential of prompting speech LMs in the domain of speech processing. We reformulate speech processing tasks into speech-to-unit generation tasks. We show that the prompting method can achieve competitive performance compared to the strong fine-tuning method.
  arXiv  Detail & Related papers  (2024-08-23T13:00:10Z)
• Cross-Lingual Transfer Learning for Speech Translation [7.802021866251242]
  This paper examines how to expand the speech translation capability of speech foundation models with restricted data.<n>Whisper, a speech foundation model with strong performance on speech recognition and English translation, is used as the example model.<n>Using speech-to-speech retrieval to analyse the audio representations generated by the encoder, we show that utterances from different languages are mapped to a shared semantic space.
  arXiv  Detail & Related papers  (2024-07-01T09:51:48Z)
• Teaching a Multilingual Large Language Model to Understand Multilingual Speech via Multi-Instructional Training [29.47243668154796]
  BLOOMZMMS is a novel model that integrates a multilingual LLM with a multilingual speech encoder. We demonstrate the transferability of linguistic knowledge from the text to the speech modality. Our zero-shot evaluation results confirm the robustness of our approach across multiple tasks.
  arXiv  Detail & Related papers  (2024-04-16T21:45:59Z)
• TranSentence: Speech-to-speech Translation via Language-agnostic Sentence-level Speech Encoding without Language-parallel Data [44.83532231917504]
  TranSentence is a novel speech-to-speech translation without language-parallel speech data. We train our model to generate speech based on the encoded embedding obtained from a language-agnostic sentence-level speech encoder. We extend TranSentence to multilingual speech-to-speech translation.
  arXiv  Detail & Related papers  (2024-01-17T11:52:40Z)
• Speech Translation with Large Language Models: An Industrial Practice [64.5419534101104]
  We introduce LLM-ST, a novel and effective speech translation model constructed upon a pre-trained large language model (LLM) By integrating the large language model (LLM) with a speech encoder and employing multi-task instruction tuning, LLM-ST can produce accurate timestamped transcriptions and translations. Through rigorous experimentation on English and Chinese datasets, we showcase the exceptional performance of LLM-ST.
  arXiv  Detail & Related papers  (2023-12-21T05:32:49Z)
• Textless Unit-to-Unit training for Many-to-Many Multilingual Speech-to-Speech Translation [65.13824257448564]
  This paper proposes a textless training method for many-to-many multilingual speech-to-speech translation. By treating the speech units as pseudo-text, we can focus on the linguistic content of the speech. We demonstrate that the proposed UTUT model can be effectively utilized not only for Speech-to-Speech Translation (S2ST) but also for multilingual Text-to-Speech Synthesis (T2S) and Text-to-Speech Translation (T2ST)
  arXiv  Detail & Related papers  (2023-08-03T15:47:04Z)
• AudioPaLM: A Large Language Model That Can Speak and Listen [79.44757696533709]
  We introduce AudioPaLM, a large language model for speech understanding and generation. AudioPaLM fuses text-based and speech-based language models. It can process and generate text and speech with applications including speech recognition and speech-to-speech translation.
  arXiv  Detail & Related papers  (2023-06-22T14:37:54Z)
• ComSL: A Composite Speech-Language Model for End-to-End Speech-to-Text Translation [79.66359274050885]
  We present ComSL, a speech-language model built atop a composite architecture of public pretrained speech-only and language-only models. Our approach has demonstrated effectiveness in end-to-end speech-to-text translation tasks.
  arXiv  Detail & Related papers  (2023-05-24T07:42:15Z)
• Speak Foreign Languages with Your Own Voice: Cross-Lingual Neural Codec Language Modeling [92.55131711064935]
  We propose a cross-lingual neural language model, VALL-E X, for cross-lingual speech synthesis. VALL-E X inherits strong in-context learning capabilities and can be applied for zero-shot cross-lingual text-to-speech synthesis and zero-shot speech-to-speech translation tasks. It can generate high-quality speech in the target language via just one speech utterance in the source language as a prompt while preserving the unseen speaker's voice, emotion, and acoustic environment.
  arXiv  Detail & Related papers  (2023-03-07T14:31:55Z)
• Generalizing Multimodal Pre-training into Multilingual via Language Acquisition [54.69707237195554]
  English-based Vision-Language Pre-training has achieved great success in various downstream tasks. Some efforts have been taken to generalize this success to non-English languages through Multilingual Vision-Language Pre-training. We propose a textbfMultitextbfLingual textbfAcquisition (MLA) framework that can easily generalize a monolingual Vision-Language Pre-training model into multilingual.
  arXiv  Detail & Related papers  (2022-05-29T08:53:22Z)
• Towards Language Modelling in the Speech Domain Using Sub-word Linguistic Units [56.52704348773307]
  We propose a novel LSTM-based generative speech LM based on linguistic units including syllables and phonemes. With a limited dataset, orders of magnitude smaller than that required by contemporary generative models, our model closely approximates babbling speech. We show the effect of training with auxiliary text LMs, multitask learning objectives, and auxiliary articulatory features.
  arXiv  Detail & Related papers  (2021-10-31T22:48:30Z)
• Bridging the Modality Gap for Speech-to-Text Translation [57.47099674461832]
  End-to-end speech translation aims to translate speech in one language into text in another language via an end-to-end way. Most existing methods employ an encoder-decoder structure with a single encoder to learn acoustic representation and semantic information simultaneously. We propose a Speech-to-Text Adaptation for Speech Translation model which aims to improve the end-to-end model performance by bridging the modality gap between speech and text.
  arXiv  Detail & Related papers  (2020-10-28T12:33:04Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.