Kimi-Audio Technical Report

We present Kimi-Audio, an open-source audio foundation model that excels in audio understanding, generation, and conversation. We detail the practices in building Kimi-Audio, including model architecture, data curation, training recipe, inference deployment, and evaluation. Specifically, we leverage a 12.5Hz audio tokenizer, design a novel LLM-based architecture with continuous features as input and discrete tokens as output, and develop a chunk-wise streaming detokenizer based on flow matching. We curate a pre-training dataset that consists of more than 13 million hours of audio data covering a wide range of modalities including speech, sound, and music, and build a pipeline to construct high-quality and diverse post-training data. Initialized from a pre-trained LLM, Kimi-Audio is continual pre-trained on both audio and text data with several carefully designed tasks, and then fine-tuned to support a diverse of audio-related tasks. Extensive evaluation shows that Kimi-Audio achieves state-of-the-art performance on a range of audio benchmarks including speech recognition, audio understanding, audio question answering, and speech conversation. We release the codes, model checkpoints, as well as the evaluation toolkits in https://github.com/MoonshotAI/Kimi-Audio.

Advancing Arabic Speech Recognition Through Large-Scale Weakly Supervised Learning

Automatic speech recognition (ASR) is crucial for human-machine interaction in diverse applications like conversational agents, industrial robotics, call center automation, and automated subtitling. However, developing high-performance ASR models remains challenging, particularly for low-resource languages like Arabic, due to the scarcity of large, labeled speech datasets, which are costly and labor-intensive to produce. In this work, we employ weakly supervised learning to train an Arabic ASR model using the Conformer architecture. Our model is trained from scratch on 15,000 hours of weakly annotated speech data covering both Modern Standard Arabic (MSA) and Dialectal Arabic (DA), eliminating the need for costly manual transcriptions. Despite the absence of human-verified labels, our approach attains state-of-the-art (SOTA) performance, exceeding all previous efforts in the field of Arabic ASR on the standard benchmarks. By demonstrating the effectiveness of weak supervision as a scalable, cost-efficient alternative to traditional supervised approaches, paving the way for improved ASR systems in low resource settings.

StableQuant: Layer Adaptive Post-Training Quantization for Speech Foundation Models

In this paper, we propose StableQuant, a novel adaptive post-training quantization (PTQ) algorithm for widely used speech foundation models (SFMs). While PTQ has been successfully employed for compressing large language models (LLMs) due to its ability to bypass additional fine-tuning, directly applying these techniques to SFMs may not yield optimal results, as SFMs utilize distinct network architecture for feature extraction. StableQuant demonstrates optimal quantization performance regardless of the network architecture type, as it adaptively determines the quantization range for each layer by analyzing both the scale distributions and overall performance. We evaluate our algorithm on two SFMs, HuBERT and wav2vec2.0, for an automatic speech recognition (ASR) task, and achieve superior performance compared to traditional PTQ methods. StableQuant successfully reduces the sizes of SFM models to a quarter and doubles the inference speed while limiting the word error rate (WER) performance drop to less than 0.3% with 8-bit quantization.

PsyCounAssist: A Full-Cycle AI-Powered Psychological Counseling Assistant System

Psychological counseling is a highly personalized and dynamic process that requires therapists to continuously monitor emotional changes, document session insights, and maintain therapeutic continuity. In this paper, we introduce PsyCounAssist, a comprehensive AI-powered counseling assistant system specifically designed to augment psychological counseling practices. PsyCounAssist integrates multimodal emotion recognition combining speech and photoplethysmography (PPG) signals for accurate real-time affective analysis, automated structured session reporting using large language models (LLMs), and personalized AI-generated follow-up support. Deployed on Android-based tablet devices, the system demonstrates practical applicability and flexibility in real-world counseling scenarios. Experimental evaluation confirms the reliability of PPG-based emotional classification and highlights the system's potential for non-intrusive, privacy-aware emotional support. PsyCounAssist represents a novel approach to ethically and effectively integrating AI into psychological counseling workflows.

LiveCC: Learning Video LLM with Streaming Speech Transcription at Scale

Recent video large language models (Video LLMs) often depend on costly human annotations or proprietary model APIs (e.g., GPT-4o) to produce training data, which limits their training at scale. In this paper, we explore large-scale training for Video LLM with cheap automatic speech recognition (ASR) transcripts. Specifically, we propose a novel streaming training approach that densely interleaves the ASR words and video frames according to their timestamps. Compared to previous studies in vision-language representation with ASR, our method naturally fits the streaming characteristics of ASR, thus enabling the model to learn temporally-aligned, fine-grained vision-language modeling. To support the training algorithm, we introduce a data production pipeline to process YouTube videos and their closed captions (CC, same as ASR), resulting in Live-CC-5M dataset for pre-training and Live-WhisperX-526K dataset for high-quality supervised fine-tuning (SFT). Remarkably, even without SFT, the ASR-only pre-trained LiveCC-7B-Base model demonstrates competitive general video QA performance and exhibits a new capability in real-time video commentary. To evaluate this, we carefully design a new LiveSports-3K benchmark, using LLM-as-a-judge to measure the free-form commentary. Experiments show our final LiveCC-7B-Instruct model can surpass advanced 72B models (Qwen2.5-VL-72B-Instruct, LLaVA-Video-72B) in commentary quality even working in a real-time mode. Meanwhile, it achieves state-of-the-art results at the 7B/8B scale on popular video QA benchmarks such as VideoMME and OVOBench, demonstrating the broad generalizability of our approach. All resources of this paper have been released at https://showlab.github.io/livecc.

Dysarthria Normalization via Local Lie Group Transformations for Robust ASR

We present a geometry-driven method for normalizing dysarthric speech using local Lie group transformations of spectrograms. Time, frequency, and amplitude distortions are modeled as smooth, invertible deformations, parameterized by scalar fields and applied via exponential maps. A neural network is trained to infer these fields from synthetic distortions of typical speech-without using any pathological data. At test time, the model applies an approximate inverse to real dysarthric inputs. Despite zero-shot generalization, we observe substantial ASR gains, including up to 16 percentage points WER reduction on challenging TORGO samples, with no degradation on clean speech. This work introduces a principled, interpretable approach for robust speech recognition under motor speech disorders

DEEMO: De-identity Multimodal Emotion Recognition and Reasoning

Emotion understanding is a critical yet challenging task. Most existing approaches rely heavily on identity-sensitive information, such as facial expressions and speech, which raises concerns about personal privacy. To address this, we introduce the De-identity Multimodal Emotion Recognition and Reasoning (DEEMO), a novel task designed to enable emotion understanding using de-identified video and audio inputs. The DEEMO dataset consists of two subsets: DEEMO-NFBL, which includes rich annotations of Non-Facial Body Language (NFBL), and DEEMO-MER, an instruction dataset for Multimodal Emotion Recognition and Reasoning using identity-free cues. This design supports emotion understanding without compromising identity privacy. In addition, we propose DEEMO-LLaMA, a Multimodal Large Language Model (MLLM) that integrates de-identified audio, video, and textual information to enhance both emotion recognition and reasoning. Extensive experiments show that DEEMO-LLaMA achieves state-of-the-art performance on both tasks, outperforming existing MLLMs by a significant margin, achieving 74.49% accuracy and 74.45% F1-score in de-identity emotion recognition, and 6.20 clue overlap and 7.66 label overlap in de-identity emotion reasoning. Our work contributes to ethical AI by advancing privacy-preserving emotion understanding and promoting responsible affective computing.

Acoustic to Articulatory Inversion of Speech; Data Driven Approaches, Challenges, Applications, and Future Scope

This review is focused on the data-driven approaches applied in different applications of Acoustic-to-Articulatory Inversion (AAI) of speech. This review paper considered the relevant works published in the last ten years (2011-2021). The selection criteria includes (a) type of AAI - Speaker Dependent and Speaker Independent AAI, (b) objectives of the work - Articulatory approximation, Articulatory Feature space selection and Automatic Speech Recognition (ASR), explore the correlation between acoustic and articulatory features, and framework for Computer-assisted language training, (c) Corpus - Simultaneously recorded speech (wav) and medical imaging models such as ElectroMagnetic Articulography (EMA), Electropalatography (EPG), Laryngography, Electroglottography (EGG), X-ray Cineradiography, Ultrasound, and real-time Magnetic Resonance Imaging (rtMRI), (d) Methods or models - recent works are considered, and therefore all the works are based on machine learning, (e) Evaluation - as AAI is a non-linear regression problem, the performance evaluation is mostly done by Correlation Coefficient (CC), Root Mean Square Error (RMSE), and also considered Mean Square Error (MSE), and Mean Format Error (MFE). The practical application of the AAI model can provide a better and user-friendly interpretable image feedback system of articulatory positions, especially tongue movement. Such trajectory feedback system can be used to provide phonetic, language, and speech therapy for pathological subjects.

SoCov: Semi-Orthogonal Parametric Pooling of Covariance Matrix for Speaker Recognition

In conventional deep speaker embedding frameworks, the pooling layer aggregates all frame-level features over time and computes their mean and standard deviation statistics as inputs to subsequent segment-level layers. Such statistics pooling strategy produces fixed-length representations from variable-length speech segments. However, this method treats different frame-level features equally and discards covariance information. In this paper, we propose the Semi-orthogonal parameter pooling of Covariance matrix (SoCov) method. The SoCov pooling computes the covariance matrix from the self-attentive frame-level features and compresses it into a vector using the semi-orthogonal parametric vectorization, which is then concatenated with the weighted standard deviation vector to form inputs to the segment-level layers. Deep embedding based on SoCov is called ``sc-vector''. The proposed sc-vector is compared to several different baselines on the SRE21 development and evaluation sets. The sc-vector system significantly outperforms the conventional x-vector system, with a relative reduction in EER of 15.5% on SRE21Eval. When using self-attentive deep feature, SoCov helps to reduce EER on SRE21Eval by about 30.9% relatively to the conventional ``mean + standard deviation'' statistics.

Optimism, Expectation, or Sarcasm? Multi-Class Hope Speech Detection in Spanish and English

Hope is a complex and underexplored emotional state that plays a significant role in education, mental health, and social interaction. Unlike basic emotions, hope manifests in nuanced forms ranging from grounded optimism to exaggerated wishfulness or sarcasm, making it difficult for Natural Language Processing systems to detect accurately. This study introduces PolyHope V2, a multilingual, fine-grained hope speech dataset comprising over 30,000 annotated tweets in English and Spanish. This resource distinguishes between four hope subtypes Generalized, Realistic, Unrealistic, and Sarcastic and enhances existing datasets by explicitly labeling sarcastic instances. We benchmark multiple pretrained transformer models and compare them with large language models (LLMs) such as GPT 4 and Llama 3 under zero-shot and few-shot regimes. Our findings show that fine-tuned transformers outperform prompt-based LLMs, especially in distinguishing nuanced hope categories and sarcasm. Through qualitative analysis and confusion matrices, we highlight systematic challenges in separating closely related hope subtypes. The dataset and results provide a robust foundation for future emotion recognition tasks that demand greater semantic and contextual sensitivity across languages.