# SSR: Alignment-Aware Modality Connector for Speech Language Models

arXiv: https://arxiv.org/abs/2410.00168 · HTML: https://mlsanity.com/paper/2410.00168/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- Builds on 45 of its 62 references that are in the map.
- First posted on arXiv 30 Sep 2024.

## Builds on (most cited first, 30 of 45)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [PaLM: Scaling Language Modeling with Pathways](https://mlsanity.com/paper/2204.02311/) (2022)
- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units](https://mlsanity.com/paper/2106.07447/) (2021)
- [Conformer: Convolution-augmented Transformer for Speech Recognition](https://mlsanity.com/paper/2005.08100/) (2020)
- [mT5: A massively multilingual pre-trained text-to-text transformer](https://mlsanity.com/paper/2010.11934/) (2020)
- [Chameleon: Mixed-Modal Early-Fusion Foundation Models](https://mlsanity.com/paper/2405.09818/) (2024)
- [SoundStream: An End-to-End Neural Audio Codec](https://mlsanity.com/paper/2107.03312/) (2021)
- [PyTorch FSDP: Experiences on Scaling Fully Sharded Data Parallel](https://mlsanity.com/paper/2304.11277/) (2023)
- [AudioLM: a Language Modeling Approach to Audio Generation](https://mlsanity.com/paper/2209.03143/) (2022)
- [XLS-R: Self-supervised Cross-lingual Speech Representation Learning at Scale](https://mlsanity.com/paper/2111.09296/) (2021)
- [Moshi: a speech-text foundation model for real-time dialogue](https://mlsanity.com/paper/2410.00037/) (2024)
- [LLaMA-VID: An Image is Worth 2 Tokens in Large Language Models](https://mlsanity.com/paper/2311.17043/) (2023)
- [SpeechGPT: Empowering Large Language Models with Intrinsic Cross-Modal Conversational Abilities](https://mlsanity.com/paper/2305.11000/) (2023)
- [VideoPoet: A Large Language Model for Zero-Shot Video Generation](https://mlsanity.com/paper/2312.14125/) (2023)
- [MLS: A Large-Scale Multilingual Dataset for Speech Research](https://mlsanity.com/paper/2012.03411/) (2020)
- [Scaling Speech Technology to 1,000+ Languages](https://mlsanity.com/paper/2305.13516/) (2023)
- [W2v-BERT: Combining Contrastive Learning and Masked Language Modeling for Self-Supervised Speech Pre-Training](https://mlsanity.com/paper/2108.06209/) (2021)
- [AudioPaLM: A Large Language Model That Can Speak and Listen](https://mlsanity.com/paper/2306.12925/) (2023)
- [Generative Spoken Language Modeling from Raw Audio](https://mlsanity.com/paper/2102.01192/) (2021)
- [Glow-TTS: A Generative Flow for Text-to-Speech via Monotonic Alignment Search](https://mlsanity.com/paper/2005.11129/) (2020)
- [AudioGPT: Understanding and Generating Speech, Music, Sound, and Talking Head](https://mlsanity.com/paper/2304.12995/) (2023)
- [Seamless: Multilingual Expressive and Streaming Speech Translation](https://mlsanity.com/paper/2312.05187/) (2023)
- [Macaw-LLM: Multi-Modal Language Modeling with Image, Audio, Video, and Text Integration](https://mlsanity.com/paper/2306.09093/) (2023)
- [On decoder-only architecture for speech-to-text and large language model integration](https://mlsanity.com/paper/2307.03917/) (2023)

## Built on by (most cited first, 16 of 16)

- [Adaptive Audio-Visual Speech Recognition via Matryoshka-Based Multimodal LLMs](https://mlsanity.com/paper/2503.06362/) (2025)
- [Voila: Voice-Language Foundation Models for Real-Time Autonomous Interaction and Voice Role-Play](https://mlsanity.com/paper/2505.02707/) (2025)
- [Scaling and Enhancing LLM-based AVSR: A Sparse Mixture of Projectors Approach](https://mlsanity.com/paper/2505.14336/) (2025)
- [Can LLMs Understand Unvoiced Speech? Exploring EMG-to-Text Conversion with LLMs](https://mlsanity.com/paper/2506.00304/) (2025)
- [LegoSLM: Connecting LLM with Speech Encoder using CTC Posteriors](https://mlsanity.com/paper/2505.11352/) (2025)
- [MoME: Mixture of Matryoshka Experts for Audio-Visual Speech Recognition](https://mlsanity.com/paper/2510.04136/) (2025)
- [SpeechMapper: Speech-to-text Embedding Projector for LLMs](https://mlsanity.com/paper/2601.20417/) (2026)
- [Beyond Fixed Frames: Dynamic Character-Aligned Speech Tokenization](https://mlsanity.com/paper/2601.23174/) (2026)
- [Bias in the Ear of the Listener: Assessing Sensitivity in Audio Language Models Across Linguistic, Demographic, and Positional Variations](https://mlsanity.com/paper/2602.01030/) (2026)
- [ALAS: An Automatic Latent Alignment Score for Audio Language Models](https://mlsanity.com/paper/2505.19937/) (2025)
- [Language Models as Semantic Teachers: Post-Training Alignment for Medical Audio Understanding](https://mlsanity.com/paper/2512.04847/) (2025)
- [Is Text All You Need? Text as a Universal Information Bottleneck for Speech LLMs](https://mlsanity.com/paper/2606.09366/) (2026)
- [Seeing is Believing: Emotion-Aware Audio-Visual Language Modeling for Expressive Speech Generation](https://mlsanity.com/paper/2508.16188/) (2025)
- [Speech2Grasp: Data-Efficient Transfer of Text-Conditioned Grasp Detection to Speech in Humanoid Robots](https://mlsanity.com/paper/2607.26567/) (2026)
- [Align, Integrate, and Fire: Efficient Token-Level Alignment for Zero-Shot SpeechLLMs](https://mlsanity.com/paper/2609.18516/) (2026)
- [Symbiotic Architecture for Post-Hoc Audio Extension of Frozen Language Models](https://mlsanity.com/paper/2609.30784/) (2026)

## Abstract (arXiv)

Fusing speech into pre-trained language model (SpeechLM) usually suffers from inefficient encoding of long-form speech and catastrophic forgetting of pre-trained text modality. We propose SSR-Connector (Segmented Speech Representation Connector) for better modality fusion. Leveraging speech-text alignments, our approach segments and compresses speech features to match the granularity of text embeddings. Additionally, we introduce a two-stage training pipeline that includes the distillation and fine-tuning phases to mitigate catastrophic forgetting. SSR-Connector outperforms existing mechanism for speech-text modality fusion, consistently achieving better speech understanding (e.g., +10 accuracy on StoryCloze and +20 on Speech-MMLU) while preserving pre-trained text ability.