Xilin Jiang

Xilin Jiang, Yinghao Aaron Li, Adrian Nicolas Florea et al.

It is too early to conclude that Mamba is a better alternative to transformers for speech before comparing Mamba with transformers in terms of both performance and efficiency in multiple speech-related tasks. To reach this conclusion, we propose and evaluate three models for three tasks: Mamba-TasNet for speech separation, ConMamba for speech recognition, and VALL-M for speech synthesis. We compare them with transformers of similar sizes in performance, memory, and speed. Our Mamba or Mamba-transformer hybrid models show comparable or higher performance than their transformer counterparts: Sepformer, Conformer, and VALL-E. They are more efficient than transformers in memory and speed for speech longer than a threshold duration, inversely related to the resolution of a speech token. Mamba for separation is the most efficient, and Mamba for recognition is the least. Further, we show that Mamba is not more efficient than transformer for speech shorter than the threshold duration and performs worse in models that require joint modeling of text and speech, such as cross or masked attention of two inputs. Therefore, we argue that the superiority of Mamba or transformer depends on particular problems and models. Code available at https://github.com/xi-j/Mamba-TasNet and https://github.com/xi-j/Mamba-ASR.

Zhepei Wang, Cem Subakan, Xilin Jiang et al. · uw

In this paper, we work on a sound recognition system that continually incorporates new sound classes. Our main goal is to develop a framework where the model can be updated without relying on labeled data. For this purpose, we propose adopting representation learning, where an encoder is trained using unlabeled data. This learning framework enables the study and implementation of a practically relevant use case where only a small amount of the labels is available in a continual learning context. We also make the empirical observation that a similarity-based representation learning method within this framework is robust to forgetting even if no explicit mechanism against forgetting is employed. We show that this approach obtains similar performance compared to several distillation-based continual learning methods when employed on self-supervised representation learning methods.

Junkai Wu, Xulin Fan, Bo-Ru Lu et al. · uw

In recent years, we have observed a rapid advancement in speech language models (SpeechLLMs), catching up with humans' listening and reasoning abilities. SpeechLLMs have demonstrated impressive spoken dialog question-answering (SQA) performance in benchmarks like Gaokao, the English listening test of the college entrance exam in China, which seemingly requires understanding both the spoken content and voice characteristics of speakers in a conversation. However, after carefully examining Gaokao's questions, we find the correct answers to many questions can be inferred from the conversation transcript alone, i.e.\ without speaker segmentation and identification. Our evaluation of state-of-the-art models Qwen-Audio and WavLLM on both Gaokao and our proposed "What Do You Like?" dataset shows a significantly higher accuracy in these context-based questions than in identity-critical questions, which can only be answered reliably with correct speaker identification. The results and analysis suggest that when solving SQA, the current SpeechLLMs exhibit limited speaker awareness from the audio and behave similarly to an LLM reasoning from the conversation transcription without sound. We propose that tasks focused on identity-critical questions could offer a more accurate evaluation framework of SpeechLLMs in SQA.

Yinghao Aaron Li, Cong Han, Xilin Jiang et al.

Large-scale pre-trained language models have been shown to be helpful in improving the naturalness of text-to-speech (TTS) models by enabling them to produce more naturalistic prosodic patterns. However, these models are usually word-level or sup-phoneme-level and jointly trained with phonemes, making them inefficient for the downstream TTS task where only phonemes are needed. In this work, we propose a phoneme-level BERT (PL-BERT) with a pretext task of predicting the corresponding graphemes along with the regular masked phoneme predictions. Subjective evaluations show that our phoneme-level BERT encoder has significantly improved the mean opinion scores (MOS) of rated naturalness of synthesized speech compared with the state-of-the-art (SOTA) StyleTTS baseline on out-of-distribution (OOD) texts.

Sukru Samet Dindar, Riki Shimizu, Xilin Jiang et al.

Empathetic spoken dialogue systems must infer a user's emotional state to respond appropriately, yet everyday speech often carries weak, neutral, or ambiguous affective cues. To address this, we introduce Sympatheia, a speech-to-speech dialogue framework conditioned on affect inferred from the user's speech and, when available, explicit affect specifications provided as a continuous valence--arousal (VA) control signal by a multimodal sensing module or user interface. To train our model, we construct Sympatheia-18k, an emotion-conditioned synthetic spoken dialogue corpus with 12 emotion anchors. This dataset includes an emotional split for learning affective speech behavior, and a neutral split that pairs emotionally neutral queries with multiple emotion-conditioned responses to isolate explicit emotion control in emotionally ambiguous cases. Empirical results show that Sympatheia outperforms speech conversational baselines in generating responses whose semantic content and spoken delivery are both emotionally appropriate. We further show that the same VA interface can integrate emotion estimates from diverse sensing modules, including facial expression, biosignals, and textual affect descriptions, improving response alignment when speech alone provides limited emotional evidence. These results suggest that continuous affect conditioning is an effective practical step for building emotionally adaptive voice assistants.

Yinghao Aaron Li, Xilin Jiang, Jordan Darefsky et al.

The rapid advancement of large language models (LLMs) has significantly propelled the development of text-based chatbots, demonstrating their capability to engage in coherent and contextually relevant dialogues. However, extending these advancements to enable end-to-end speech-to-speech conversation bots remains a formidable challenge, primarily due to the extensive dataset and computational resources required. The conventional approach of cascading automatic speech recognition (ASR), LLM, and text-to-speech (TTS) models in a pipeline, while effective, suffers from unnatural prosody because it lacks direct interactions between the input audio and its transcribed text and the output audio. These systems are also limited by their inherent latency from the ASR process for real-time applications. This paper introduces Style-Talker, an innovative framework that fine-tunes an audio LLM alongside a style-based TTS model for fast spoken dialog generation. Style-Talker takes user input audio and uses transcribed chat history and speech styles to generate both the speaking style and text for the response. Subsequently, the TTS model synthesizes the speech, which is then played back to the user. While the response speech is being played, the input speech undergoes ASR processing to extract the transcription and speaking style, serving as the context for the ensuing dialogue turn. This novel pipeline accelerates the traditional cascade ASR-LLM-TTS systems while integrating rich paralinguistic information from input speech. Our experimental results show that Style-Talker significantly outperforms the conventional cascade and speech-to-speech baselines in terms of both dialogue naturalness and coherence while being more than 50% faster.

Xilin Jiang, Cong Han, Yinghao Aaron Li et al.

In this study, we present a simple multi-channel framework for contrastive learning (MC-SimCLR) to encode 'what' and 'where' of spatial audios. MC-SimCLR learns joint spectral and spatial representations from unlabeled spatial audios, thereby enhancing both event classification and sound localization in downstream tasks. At its core, we propose a multi-level data augmentation pipeline that augments different levels of audio features, including waveforms, Mel spectrograms, and generalized cross-correlation (GCC) features. In addition, we introduce simple yet effective channel-wise augmentation methods to randomly swap the order of the microphones and mask Mel and GCC channels. By using these augmentations, we find that linear layers on top of the learned representation significantly outperform supervised models in terms of both event classification accuracy and localization error. We also perform a comprehensive analysis of the effect of each augmentation method and a comparison of the fine-tuning performance using different amounts of labeled data.

Yinghao Aaron Li, Cong Han, Xilin Jiang et al.

Recent advancements in speech synthesis have leveraged GAN-based networks like HiFi-GAN and BigVGAN to produce high-fidelity waveforms from mel-spectrograms. However, these networks are computationally expensive and parameter-heavy. iSTFTNet addresses these limitations by integrating inverse short-time Fourier transform (iSTFT) into the network, achieving both speed and parameter efficiency. In this paper, we introduce an extension to iSTFTNet, termed HiFTNet, which incorporates a harmonic-plus-noise source filter in the time-frequency domain that uses a sinusoidal source from the fundamental frequency (F0) inferred via a pre-trained F0 estimation network for fast inference speed. Subjective evaluations on LJSpeech show that our model significantly outperforms both iSTFTNet and HiFi-GAN, achieving ground-truth-level performance. HiFTNet also outperforms BigVGAN-base on LibriTTS for unseen speakers and achieves comparable performance to BigVGAN while being four times faster with only $1/6$ of the parameters. Our work sets a new benchmark for efficient, high-quality neural vocoding, paving the way for real-time applications that demand high quality speech synthesis.

Xilin Jiang, Sukru Samet Dindar, Vishal Choudhari et al.

Auditory foundation models, including auditory large language models (LLMs), process all sound inputs equally, independent of listener perception. However, human auditory perception is inherently selective: listeners focus on specific speakers while ignoring others in complex auditory scenes. Existing models do not incorporate this selectivity, limiting their ability to generate perception-aligned responses. To address this, we introduce Intention-Informed Auditory Scene Understanding (II-ASU) and present Auditory Attention-Driven LLM (AAD-LLM), a prototype system that integrates brain signals to infer listener attention. AAD-LLM extends an auditory LLM by incorporating intracranial electroencephalography (iEEG) recordings to decode which speaker a listener is attending to and refine responses accordingly. The model first predicts the attended speaker from neural activity, then conditions response generation on this inferred attentional state. We evaluate AAD-LLM on speaker description, speech transcription and extraction, and question answering in multitalker scenarios, with both objective and subjective ratings showing improved alignment with listener intention. By taking a first step toward intention-aware auditory AI, this work explores a new paradigm where listener perception informs machine listening, paving the way for future listener-centered auditory systems. Demo and code available: https://aad-llm.github.io.

Long Phan, Alice Gatti, Ziwen Han et al. · amazon-science, apple-ml

Benchmarks are important tools for tracking the rapid advancements in large language model (LLM) capabilities. However, benchmarks are not keeping pace in difficulty: LLMs now achieve over 90\% accuracy on popular benchmarks like MMLU, limiting informed measurement of state-of-the-art LLM capabilities. In response, we introduce Humanity's Last Exam (HLE), a multi-modal benchmark at the frontier of human knowledge, designed to be the final closed-ended academic benchmark of its kind with broad subject coverage. HLE consists of 2,500 questions across dozens of subjects, including mathematics, humanities, and the natural sciences. HLE is developed globally by subject-matter experts and consists of multiple-choice and short-answer questions suitable for automated grading. Each question has a known solution that is unambiguous and easily verifiable, but cannot be quickly answered via internet retrieval. State-of-the-art LLMs demonstrate low accuracy and calibration on HLE, highlighting a significant gap between current LLM capabilities and the expert human frontier on closed-ended academic questions. To inform research and policymaking upon a clear understanding of model capabilities, we publicly release HLE at https://lastexam.ai.

Siavash Shams, Sukru Samet Dindar, Xilin Jiang et al.

Transformers have revolutionized deep learning across various tasks, including audio representation learning, due to their powerful modeling capabilities. However, they often suffer from quadratic complexity in both GPU memory usage and computational inference time, affecting their efficiency. Recently, state space models (SSMs) like Mamba have emerged as a promising alternative, offering a more efficient approach by avoiding these complexities. Given these advantages, we explore the potential of SSM-based models in audio tasks. In this paper, we introduce Self-Supervised Audio Mamba (SSAMBA), the first self-supervised, attention-free, and SSM-based model for audio representation learning. SSAMBA leverages the bidirectional Mamba to capture complex audio patterns effectively. We incorporate a self-supervised pretraining framework that optimizes both discriminative and generative objectives, enabling the model to learn robust audio representations from large-scale, unlabeled datasets. We evaluated SSAMBA on various tasks such as audio classification, keyword spotting, and speaker identification. Our results demonstrate that SSAMBA outperforms the Self-Supervised Audio Spectrogram Transformer (SSAST) in most tasks. Notably, SSAMBA is approximately 92.7% faster in batch inference speed and 95.4% more memory-efficient than SSAST for the tiny model size with an input token size of 22k. These efficiency gains, combined with superior performance, underscore the effectiveness of SSAMBA's architectural innovation, making it a compelling choice for a wide range of audio processing applications.

Xilin Jiang, Cong Han, Yinghao Aaron Li et al.

In daily life, we encounter a variety of sounds, both desirable and undesirable, with limited control over their presence and volume. Our work introduces "Listen, Chat, and Remix" (LCR), a novel multimodal sound remixer that controls each sound source in a mixture based on user-provided text instructions. LCR distinguishes itself with a user-friendly text interface and its unique ability to remix multiple sound sources simultaneously within a mixture, without needing to separate them. Users input open-vocabulary text prompts, which are interpreted by a large language model to create a semantic filter for remixing the sound mixture. The system then decomposes the mixture into its components, applies the semantic filter, and reassembles filtered components back to the desired output. We developed a 160-hour dataset with over 100k mixtures, including speech and various audio sources, along with text prompts for diverse remixing tasks including extraction, removal, and volume control of single or multiple sources. Our experiments demonstrate significant improvements in signal quality across all remixing tasks and robust performance in zero-shot scenarios with varying numbers and types of sound sources. An audio demo is available at: https://listenchatremix.github.io/demo.

Zhongweiyang Xu, Xulin Fan, Zhong-Qiu Wang et al.

Blind Speech Separation (BSS) aims to separate multiple speech sources from audio mixtures recorded by a microphone array. The problem is challenging because it is a blind inverse problem, i.e., the microphone array geometry, the room impulse response (RIR), and the speech sources, are all unknown. We propose ArrayDPS to solve the BSS problem in an unsupervised, array-agnostic, and generative manner. The core idea builds on diffusion posterior sampling (DPS), but unlike DPS where the likelihood is tractable, ArrayDPS must approximate the likelihood by formulating a separate optimization problem. The solution to the optimization approximates room acoustics and the relative transfer functions between microphones. These approximations, along with the diffusion priors, iterate through the ArrayDPS sampling process and ultimately yield separated voice sources. We only need a simple single-speaker speech diffusion model as a prior along with the mixtures recorded at the microphones; no microphone array information is necessary. Evaluation results show that ArrayDPS outperforms all baseline unsupervised methods while being comparable to supervised methods in terms of SDR. Audio demos are provided at: https://arraydps.github.io/ArrayDPSDemo/.

Adrian Florea, Xilin Jiang, Nima Mesgarani et al.

Large language models (LLMs) for audio have excelled in recognizing and analyzing human speech, music, and environmental sounds. However, their potential for understanding other types of sounds, particularly biomedical sounds, remains largely underexplored despite significant scientific interest. In this study, we focus on diagnosing cardiovascular diseases using phonocardiograms, i.e., heart sounds. Most existing deep neural network (DNN) paradigms are restricted to heart murmur classification (healthy vs unhealthy) and do not predict other acoustic features of the murmur such as timing, grading, harshness, pitch, and quality, which are important in helping physicians diagnose the underlying heart conditions. We propose to finetune an audio LLM, Qwen2-Audio, on the PhysioNet CirCor DigiScope phonocardiogram (PCG) dataset and evaluate its performance in classifying 11 expert-labeled murmur features. Additionally, we aim to achieve more noise-robust and generalizable system by exploring a preprocessing segmentation algorithm using an audio representation model, SSAMBA. Our results indicate that the LLM-based model outperforms state-of-the-art methods in 8 of the 11 features and performs comparably in the remaining 3. Moreover, the LLM successfully classifies long-tail murmur features with limited training data, a task that all previous methods have failed to classify. These findings underscore the potential of audio LLMs as assistants to human cardiologists in enhancing heart disease diagnosis.

Xilin Jiang, Junkai Wu, Vishal Choudhari et al. · uw

Audio large language models (LLMs) are considered experts at recognizing sound objects, yet their performance relative to LLMs in other sensory modalities, such as visual or audio-visual LLMs, and to humans using their ears, eyes, or both remains unexplored. To investigate this, we systematically evaluate audio, visual, and audio-visual LLMs, specifically Qwen2-Audio, Qwen2-VL, and Qwen2.5-Omni, against humans in recognizing sound objects of different classes from audio-only, silent video, or sounded video inputs. We uncover a performance gap between Qwen2-Audio and Qwen2-VL that parallels the sensory discrepancy between human ears and eyes. To reduce this gap, we introduce a cross-modal distillation framework, where an LLM in one modality serves as the teacher and another as the student, with knowledge transfer in sound classes predicted as more challenging to the student by a heuristic model. Distillation in both directions, from Qwen2-VL to Qwen2-Audio and vice versa, leads to notable improvements, particularly in challenging classes. This work highlights the sensory gap in LLMs from a human-aligned perspective and proposes a principled approach to enhancing modality-specific perception in multimodal LLMs.

Linyang He, Qiaolin Wang, Xilin Jiang et al.

Transformer-based speech language models (SLMs) have significantly improved neural speech recognition and understanding. While existing research has examined how well SLMs encode shallow acoustic and phonetic features, the extent to which SLMs encode nuanced syntactic and conceptual features remains unclear. By drawing parallels with linguistic competence assessments for large language models, this study is the first to systematically evaluate the presence of contextual syntactic and semantic features across SLMs for self-supervised learning (S3M), automatic speech recognition (ASR), speech compression (codec), and as the encoder for auditory large language models (AudioLLMs). Through minimal pair designs and diagnostic feature analysis across 71 tasks spanning diverse linguistic levels, our layer-wise and time-resolved analysis uncovers that 1) all speech encode grammatical features more robustly than conceptual ones.

Xilin Jiang, Qiaolin Wang, Junkai Wu et al.

Internet audio-visual clips convey meaning through time-varying sound and motion, which extend beyond what text alone can represent. To examine whether AI models can understand such signals in human cultural contexts, we introduce AVMeme Exam, a human-curated benchmark of over one thousand iconic Internet sounds and videos spanning speech, songs, music, and sound effects. Each meme is paired with a unique Q&A assessing levels of understanding from surface content to context and emotion to usage and world knowledge, along with metadata such as original year, transcript, summary, and sensitivity. We systematically evaluate state-of-the-art multimodal large language models (MLLMs) alongside human participants using this benchmark. Our results reveal a consistent limitation: current models perform poorly on textless music and sound effects, and struggle to think in context and in culture compared to surface content. These findings highlight a key gap in human-aligned multimodal intelligence and call for models that can perceive contextually and culturally beyond the surface of what they hear and see. Project page: avmemeexam.github.io/public

Xilin Jiang, Hannes Gamper, Sebastian Braun

Acoustic scene perception involves describing the type of sounds, their timing, their direction and distance, as well as their loudness and reverberation. While audio language models excel in sound recognition, single-channel input fundamentally limits spatial understanding. This work presents Sci-Phi, a spatial audio large language model with dual spatial and spectral encoders that estimates a complete parameter set for all sound sources and the surrounding environment. Learning from over 4,000 hours of synthetic first-order Ambisonics recordings including metadata, Sci-Phi enumerates and describes up to four directional sound sources in one pass, alongside non-directional background sounds and room characteristics. We evaluate the model with a permutation-invariant protocol and 15 metrics covering content, location, timing, loudness, and reverberation, and analyze its robustness across source counts, signal-to-noise ratios, reverberation levels, and challenging mixtures of acoustically, spatially, or temporally similar sources. Notably, Sci-Phi generalizes to real room impulse responses with only minor performance degradation. Overall, this work establishes the first audio LLM capable of full spatial-scene description, with strong potential for real-world deployment. Demo: https://sci-phi-audio.github.io/demo

Qiaolin Wang, Xilin Jiang, Linyang He et al. · uw

While large audio-language models (LALMs) have demonstrated state-of-the-art audio understanding, their reasoning capability in complex soundscapes still falls behind large vision-language models (LVLMs). Compared to the visual domain, one bottleneck is the lack of large-scale chain-of-thought audio data to teach LALM stepwise reasoning. To circumvent this data and modality gap, we present SightSound-R1, a cross-modal distillation framework that transfers advanced reasoning from a stronger LVLM teacher to a weaker LALM student on the same audio-visual question answering (AVQA) dataset. SightSound-R1 consists of three core steps: (i) test-time scaling to generate audio-focused chains of thought (CoT) from an LVLM teacher, (ii) audio-grounded validation to filter hallucinations, and (iii) a distillation pipeline with supervised fine-tuning (SFT) followed by Group Relative Policy Optimization (GRPO) for the LALM student. Results show that SightSound-R1 improves LALM reasoning performance both in the in-domain AVQA test set as well as in unseen auditory scenes and questions, outperforming both pretrained and label-only distilled baselines. Thus, we conclude that vision reasoning can be effectively transferred to audio models and scaled with abundant audio-visual data.

Xilin Jiang, Yinghao Aaron Li, Nima Mesgarani

Lifelong audio feature extraction involves learning new sound classes incrementally, which is essential for adapting to new data distributions over time. However, optimizing the model only on new data can lead to catastrophic forgetting of previously learned tasks, which undermines the model's ability to perform well over the long term. This paper introduces a new approach to continual audio representation learning called DeCoR. Unlike other methods that store previous data, features, or models, DeCoR indirectly distills knowledge from an earlier model to the latest by predicting quantization indices from a delayed codebook. We demonstrate that DeCoR improves acoustic scene classification accuracy and integrates well with continual self-supervised representation learning. Our approach introduces minimal storage and computation overhead, making it a lightweight and efficient solution for continual learning.

Efthymios Tzinis, Zhepei Wang, Xilin Jiang et al.

Recent progress in audio source separation lead by deep learning has enabled many neural network models to provide robust solutions to this fundamental estimation problem. In this study, we provide a family of efficient neural network architectures for general purpose audio source separation while focusing on multiple computational aspects that hinder the application of neural networks in real-world scenarios. The backbone structure of this convolutional network is the SUccessive DOwnsampling and Resampling of Multi-Resolution Features (SuDoRM-RF) as well as their aggregation which is performed through simple one-dimensional convolutions. This mechanism enables our models to obtain high fidelity signal separation in a wide variety of settings where variable number of sources are present and with limited computational resources (e.g. floating point operations, memory footprint, number of parameters and latency). Our experiments show that SuDoRM-RF models perform comparably and even surpass several state-of-the-art benchmarks with significantly higher computational resource requirements. The causal variation of SuDoRM-RF is able to obtain competitive performance in real-time speech separation of around 10dB scale-invariant signal-to-distortion ratio improvement (SI-SDRi) while remaining up to 20 times faster than real-time on a laptop device.