arXiv subjects

Eng Siong Chng

Publications and source records attributed to Eng Siong Chng.

At least 55 records · Page 3Linked to original sources

arXiv2025

Step-Audio-R1 Technical Report

Recent advances in reasoning models have demonstrated remarkable success in text and vision domains through extended chain-of-thought deliberation. However, a perplexing phenomenon persists in audio language models: they consistently perform better with minimal or no reasoning, raising a fundamental question - can audio intelligence truly benefit from deliberate thinking? We introduce Step-Audio-R1, the first audio reasoning model that successfully unlocks reasoning capabilities in the audio domain. Through our proposed Modality-Grounded Reasoning Distillation (MGRD) framework, Step-Audio-R1 learns to generate audio-relevant reasoning chains that genuinely ground themselves in acoustic features rather than hallucinating disconnected deliberations. Our model exhibits strong audio reasoning capabilities, surpassing Gemini 2.5 Pro and achieving performance comparable to the state-of-the-art Gemini 3 Pro across comprehensive audio understanding and reasoning benchmarks spanning speech, environmental sounds, and music. These results demonstrate that reasoning is a transferable capability across modalities when appropriately anchored, transforming extended deliberation from a liability into a powerful asset for audio intelligence. By establishing the first successful audio reasoning model, Step-Audio-R1 opens new pathways toward building truly multimodal reasoning systems that think deeply across all sensory modalities.

cs.AI↗

arXiv2025

Next-Frame Feature Prediction for Multimodal Deepfake Detection and Temporal Localization

Recent multimodal deepfake detection methods designed for generalization conjecture that single-stage supervised training struggles to generalize across unseen manipulations and datasets. However, such approaches that target generalization require pretraining over real samples. Additionally, these methods primarily focus on detecting audio-visual inconsistencies and may overlook intra-modal artifacts causing them to fail against manipulations that preserve audio-visual alignment. To address these limitations, we propose a single-stage training framework that enhances generalization by incorporating next-frame prediction for both uni-modal and cross-modal features. Additionally, we introduce a window-level attention mechanism to capture discrepancies between predicted and actual frames, enabling the model to detect local artifacts around every frame, which is crucial for accurately classifying fully manipulated videos and effectively localizing deepfake segments in partially spoofed samples. Our model, evaluated on multiple benchmark datasets, demonstrates strong generalization and precise temporal localization.

cs.CV↗

arXiv2025

Aligning Speech to Languages to Enhance Code-switching Speech Recognition

Code-switching (CS) refers to the switching of languages within a speech signal and results in language confusion for automatic speech recognition (ASR). To address language confusion, we propose a language alignment loss (LAL) that aligns acoustic features to pseudo-language labels learned from the ASR decoder during ASR training. This approach enables frame-level language identification without the need for frame-level language annotations. To further tackle the complex token alternatives for language modeling in bilingual scenarios, we propose to employ large language models via a generative error correction method. A linguistic hint, derived from LAL outputs and decoded hypotheses, is introduced to guide the prompting and enhance the LLM-based generative error correction for CS-ASR. The proposed methods are evaluated on the SEAME dataset and data from the ASRU 2019 Mandarin-English code-switching speech recognition challenge. The incorporation of the proposed language alignment loss improves CS-ASR performance for both hybrid CTC/attention and Whisper models on both datasets, with only a negligible increase in the number of parameters. This work also highlights the efficacy of language alignment loss in balancing primary-language-dominant bilingual data during training, with an 8.6% relative improvement on the ASRU dataset compared to the baseline model. Performance evaluation using large language models reveals the advantage of the linguistic hint by achieving 14.1% and 5.5% relative improvement on test sets of the ASRU and SEAME datasets, respectively.

eess.AS↗

arXiv2025

MULTI-Bench: A Multi-Turn Interactive Benchmark for Assessing Emotional Intelligence ability of Spoken Dialogue Models

Spoken Dialogue Models (SDMs) have advanced rapidly, yet their ability to sustain genuinely interactive multi-turn conversations remains underexplored, as most benchmarks focus on single-turn exchanges. We introduce Multi-Bench, the first benchmark explicitly designed to evaluate SDMs in multi-turn interactive dialogue with an emphasis on emotional intelligence. Multi-Bench employs a hierarchical structure with a basic track for emotion understanding and reasoning and an advanced track for emotion support and application. It comprises five carefully designed tasks and about 3.2K samples, ranging from emotion recognition to complex reasoning and interactive dialogue, supported by a reproducible evaluation framework. We evaluate six representative SDMs on eight subsets of Multi-Bench. Results show that while current SDMs achieve good performance on basic understanding tasks, they still have room for improvement in advanced multi-turn interactive dialogue and reasoning-related tasks, particularly in emotion awareness and application.

eess.AS↗

arXiv2025

Explainable Disentanglement on Discrete Speech Representations for Noise-Robust ASR

Discrete audio representations are gaining traction in speech modeling due to their interpretability and compatibility with large language models, but are not always optimized for noisy or real-world environments. Building on existing works that quantize Whisper embeddings for speech-to-unit modeling, we propose disentangling semantic speech content from background noise in the latent space. Our end-to-end model separates clean speech in the form of codebook tokens, while extracting interpretable noise vectors as quantization residue which are supervised via a lightweight classifier. We show that our approach improves alignment between clean/noisy speech and text, producing speech tokens that display a high degree of noiseinvariance, and improves ASR performance. Keeping Whisper frozen, we show an 82% reduction in error rate compared to Whisper, and 35% improvement over baseline methods on the VBDemand test set. Further analyses show that the learned token space generalizes well to both seen and unseen acoustic conditions.

cs.CL↗

arXiv2025

Summary on The Multilingual Conversational Speech Language Model Challenge: Datasets, Tasks, Baselines, and Methods

This paper summarizes the Interspeech2025 Multilingual Conversational Speech Language Model (MLC-SLM) challenge, which aims to advance the exploration of building effective multilingual conversational speech LLMs (SLLMs). We provide a detailed description of the task settings for the MLC-SLM challenge, the released real-world multilingual conversational speech dataset totaling approximately 1,604 hours, and the baseline systems for participants. The MLC-SLM challenge attracts 78 teams from 13 countries to participate, with 489 valid leaderboard results and 14 technical reports for the two tasks. We distill valuable insights on building multilingual conversational SLLMs based on submissions from participants, aiming to contribute to the advancement of the community.

eess.AS↗

arXiv2025

Improving Synthetic Data Training for Contextual Biasing Models with a Keyword-Aware Cost Function

Rare word recognition can be improved by adapting ASR models to synthetic data that includes these words. Further improvements can be achieved through contextual biasing, which trains and adds a biasing module into the model architecture to prioritize rare words. While training the module on synthetic rare word data is more effective than using non-rare-word data, it can lead to overfitting due to artifacts in the synthetic audio. To address this, we enhance the TCPGen-based contextual biasing approach and propose a keyword-aware loss function that additionally focuses on biased words when training biasing modules. This loss includes a masked cross-entropy term for biased word prediction and a binary classification term for detecting biased word positions. These two terms complementarily support the decoding of biased words during inference. By adapting Whisper to 10 hours of synthetic data, our method reduced the word error rate on the NSC Part 2 test set from 29.71% to 11.81%.

cs.CL↗

arXiv2025

Zero-shot Context Biasing with Trie-based Decoding using Synthetic Multi-Pronunciation

Contextual automatic speech recognition (ASR) systems allow for recognizing out-of-vocabulary (OOV) words, such as named entities or rare words. However, it remains challenging due to limited training data and ambiguous or inconsistent pronunciations. In this paper, we propose a synthesis-driven multi-pronunciation contextual biasing method that performs zero-shot contextual ASR on a pretrained Whisper model. Specifically, we leverage text-to-speech (TTS) systems to synthesize diverse speech samples containing each target rare word, and then use the pretrained Whisper model to extract multiple predicted pronunciation variants. These variant token sequences are compiled into a prefix-trie, which assigns rewards to beam hypotheses in a shallow-fusion manner during beam-search decoding. Subsequently, any recognized variant is mapped back to the original rare word in the final transcription. The evaluation results on the LibriSpeech dataset show that our method reduces biased-word error rate (B-WER) by 43% on test-clean and 44% on test-other while maintaining unbiased-WER (U-WER) essentially unchanged.

cs.CL↗

arXiv2025

Analysis of Speaker Verification Performance Trade-offs with Neural Audio Codec Transmission

Neural audio codecs (NACs) have made significant advancements in recent years and are rapidly being adopted in many audio processing pipelines. However, they can introduce audio distortions which degrade speaker verification (SV) performance. This study investigates the impact of both traditional and neural audio codecs at varying bitrates on three state of-the-art SV models evaluated on the VoxCeleb1 dataset. Our findings reveal a consistent degradation in SV performance across all models and codecs as bitrates decrease. Notably, NACs do not fundamentally break SV performance when compared to traditional codecs. They outperform Opus by 6-8% at low-bitrates (< 12 kbps) and remain marginally behind at higher bitrates ($\approx$ 24 kbps), with an EER increase of only 0.4-0.7%. The disparity at higher bitrates is likely due to the primary optimization of NACs for perceptual quality, which can inadvertently discard critical speaker-discriminative features, unlike Opus which was designed to preserve vocal characteristics. Our investigation suggests that NACs are a feasible alternative to traditional codecs, especially under bandwidth limitations. To bridge the gap at higher bitrates, future work should focus on developing speaker-aware NACs or retraining and adapting SV models.

cs.SD↗

arXiv2025

Robust Localization of Partially Fake Speech: Metrics and Out-of-Domain Evaluation

Partial audio deepfake localization poses unique challenges and remain underexplored compared to full-utterance spoofing detection. While recent methods report strong in-domain performance, their real-world utility remains unclear. In this analysis, we critically examine the limitations of current evaluation practices, particularly the widespread use of Equal Error Rate (EER), which often obscures generalization and deployment readiness. We propose reframing the localization task as a sequential anomaly detection problem and advocate for the use of threshold-dependent metrics such as accuracy, precision, recall, and F1-score, which better reflect real-world behavior. Specifically, we analyze the performance of the open-source Coarse-to-Fine Proposal Refinement Framework (CFPRF), which achieves a 20-ms EER of 7.61% on the in-domain PartialSpoof evaluation set, but 43.25% and 27.59% on the LlamaPartialSpoof and Half-Truth out-of-domain test sets. Interestingly, our reproduced version of the same model performs worse on in-domain data (9.84%) but better on the out-of-domain sets (41.72% and 14.98%, respectively). This highlights the risks of over-optimizing for in-domain EER, which can lead to models that perform poorly in real-world scenarios. It also suggests that while deep learning models can be effective on in-domain data, they generalize poorly to out-of-domain scenarios, failing to detect novel synthetic samples and misclassifying unfamiliar bona fide audio. Finally, we observe that adding more bona fide or fully synthetic utterances to the training data often degrades performance, whereas adding partially fake utterances improves it.

cs.SD↗

arXiv2025

Noro: Noise-Robust One-shot Voice Conversion with Hidden Speaker Representation Learning

The effectiveness of one-shot voice conversion (VC) decreases in real-world scenarios where reference speeches, which are often sourced from the internet, contain various disturbances like background noise. To address this issue, we introduce Noro, a noise-robust one-shot VC system. Noro features innovative components tailored for VC using noisy reference speeches, including a dual-branch reference encoding module and a noise-agnostic contrastive speaker loss. Experimental results demonstrate that Noro outperforms our baseline system in both clean and noisy scenarios, highlighting its efficacy for real-world applications. Additionally, we investigate the hidden speaker representation capabilities of our baseline system by repurposing its reference encoder as a speaker encoder. The results show that it is competitive with several advanced self-supervised learning models for speaker representation under the SUPERB settings, highlighting the potential for advancing speaker representation learning through one-shot VC tasks.

cs.SD↗

arXiv2025

FD-Bench: A Full-Duplex Benchmarking Pipeline Designed for Full Duplex Spoken Dialogue Systems

Full-duplex spoken dialogue systems (FDSDS) enable more natural human-machine interactions by allowing real-time user interruptions and backchanneling, compared to traditional SDS that rely on turn-taking. However, existing benchmarks lack metrics for FD scenes, e.g., evaluating model performance during user interruptions. In this paper, we present a comprehensive FD benchmarking pipeline utilizing LLMs, TTS, and ASR to address this gap. It assesses FDSDS's ability to handle user interruptions, manage delays, and maintain robustness in challenging scenarios with diverse novel metrics. We applied our benchmark to three open-source FDSDS (Moshi, Freeze-omni, and VITA-1.5) using over 40 hours of generated speech, with 293 simulated conversations and 1,200 interruptions. The results show that all models continue to face challenges, such as failing to respond to user interruptions, under frequent disruptions and noisy conditions. Demonstrations, data, and code will be released.

eess.AS↗

arXiv2025

NTU Speechlab LLM-Based Multilingual ASR System for Interspeech MLC-SLM Challenge 2025

This report details the NTU Speechlab system developed for the Interspeech 2025 Multilingual Conversational Speech and Language Model (MLC-SLM) Challenge (Task I), where we achieved 5th place. We present comprehensive analyses of our multilingual automatic speech recognition system, highlighting key advancements in model architecture, data selection, and training strategies. In particular, language-specific prompts and model averaging techniques were instrumental in boosting system performance across diverse languages. Compared to the initial baseline system, our final model reduced the average Mix Error Rate from 20.2% to 10.6%, representing an absolute improvement of 9.6% (a relative improvement of 48%) on the evaluation set. Our results demonstrate the effectiveness of our approach and offer practical insights for future Speech Large Language Models.

cs.CL↗

arXiv2025

Bi-directional Context-Enhanced Speech Large Language Models for Multilingual Conversational ASR

This paper introduces the integration of language-specific bi-directional context into a speech large language model (SLLM) to improve multilingual continuous conversational automatic speech recognition (ASR). We propose a character-level contextual masking strategy during training, which randomly removes portions of the context to enhance robustness and better emulate the flawed transcriptions that may occur during inference. For decoding, a two-stage pipeline is utilized: initial isolated segment decoding followed by context-aware re-decoding using neighboring hypotheses. Evaluated on the 1500-hour Multilingual Conversational Speech and Language Model (MLC-SLM) corpus covering eleven languages, our method achieves an 18% relative improvement compared to a strong baseline, outperforming even the model trained on 6000 hours of data for the MLC-SLM competition. These results underscore the significant benefit of incorporating contextual information in multilingual continuous conversational ASR.

cs.CL↗

arXiv2025

Impact of Frame Rates on Speech Tokenizer: A Case Study on Mandarin and English

The speech tokenizer plays a crucial role in recent speech tasks, generally serving as a bridge between speech signals and language models. While low-frame-rate codecs are widely employed as speech tokenizers, the impact of frame rates on speech tokens remains underexplored. In this study, we investigate how varying frame rates affect speech tokenization by examining Mandarin and English, two typologically distinct languages. We encode speech at different frame rates and evaluate the resulting semantic tokens in the speech recognition task. Our findings reveal that frame rate variations influence speech tokenization differently for each language, highlighting the interplay between frame rates, phonetic density, and language-specific acoustic features. The results provide insights into optimizing frame rate selection for speech tokenizers, with implications for automatic speech recognition, text-to-speech, and other speech-related applications.

cs.CL↗

arXiv2025

A correlation-permutation approach for speech-music encoders model merging

Creating a unified speech and music model requires expensive pre-training. Model merging can instead create an unified audio model with minimal computational expense. However, direct merging is challenging when the models are not aligned in the weight space. Motivated by Git Re-Basin, we introduce a correlation-permutation approach that aligns a music encoder's internal layers with a speech encoder. We extend previous work to the case of merging transformer layers. The method computes a permutation matrix that maximizes the model's features-wise cross-correlations layer by layer, enabling effective fusion of these otherwise disjoint models. The merged model retains speech capabilities through this method while significantly enhancing music performance, achieving an improvement of 14.83 points in average score compared to linear interpolation model merging. This work allows the creation of unified audio models from independently trained encoders.

cs.SD↗

arXiv2025

EASY: Emotion-aware Speaker Anonymization via Factorized Distillation

Emotion plays a significant role in speech interaction, conveyed through tone, pitch, and rhythm, enabling the expression of feelings and intentions beyond words to create a more personalized experience. However, most existing speaker anonymization systems employ parallel disentanglement methods, which only separate speech into linguistic content and speaker identity, often neglecting the preservation of the original emotional state. In this study, we introduce EASY, an emotion-aware speaker anonymization framework. EASY employs a novel sequential disentanglement process to disentangle speaker identity, linguistic content, and emotional representation, modeling each speech attribute in distinct subspaces through a factorized distillation approach. By independently constraining speaker identity and emotional representation, EASY minimizes information leakage, enhancing privacy protection while preserving original linguistic content and emotional state. Experimental results on the VoicePrivacy Challenge official datasets demonstrate that our proposed approach outperforms all baseline systems, effectively protecting speaker privacy while maintaining linguistic content and emotional state.

eess.AS↗

arXiv2025

Speechless: Speech Instruction Training Without Speech for Low Resource Languages

The rapid growth of voice assistants powered by large language models (LLM) has highlighted a need for speech instruction data to train these systems. Despite the abundance of speech recognition data, there is a notable scarcity of speech instruction data, which is essential for fine-tuning models to understand and execute spoken commands. Generating high-quality synthetic speech requires a good text-to-speech (TTS) model, which may not be available to low resource languages. Our novel approach addresses this challenge by halting synthesis at the semantic representation level, bypassing the need for TTS. We achieve this by aligning synthetic semantic representations with the pre-trained Whisper encoder, enabling an LLM to be fine-tuned on text instructions while maintaining the ability to understand spoken instructions during inference. This simplified training process is a promising approach to building voice assistant for low-resource languages.

eess.AS↗