Transcript-Prompted Whisper with Dictionary-Enhanced Decoding for Japanese Speech Annotation

In this paper, we propose a method for annotating phonemic and prosodic labels on a given audio-transcript pair, aimed at constructing Japanese text-to-speech (TTS) datasets. Our approach involves fine-tuning a large-scale pre-trained automatic speech recognition (ASR) model, conditioned on ground truth transcripts, to simultaneously output phrase-level graphemes and annotation labels. To further correct errors in phonemic labeling, we employ a decoding strategy that utilizes dictionary prior knowledge. The objective evaluation results demonstrate that our proposed method outperforms previous approaches relying solely on text or audio. The subjective evaluation results indicate that the naturalness of speech synthesized by the TTS model, trained with labels annotated using our method, is comparable to that of a model trained with manual annotations.

Exploring Length Generalization For Transformer-based Speech Enhancement

Transformer network architecture has proven effective in speech enhancement. However, as its core module, self-attention suffers from quadratic complexity, making it infeasible for training on long speech utterances. In practical scenarios, speech enhancement models are often required to perform on noisy speech at run-time that is substantially longer than the training utterances. It remains a challenge how a Transformer-based speech enhancement model can generalize to long speech utterances. In this paper, extensive empirical studies are conducted to explore the model's length generalization ability. In particular, we conduct speech enhancement experiments on four training objectives and evaluate with five metrics. Our studies establish that positional encoding is an effective instrument to dampen the effect of utterance length on speech enhancement. We first explore several existing positional encoding methods, and the results show that relative positional encoding methods exhibit a better length generalization property than absolute positional encoding methods. Additionally, we also explore a simpler and more effective positional encoding scheme, i.e. LearnLin, that uses only one trainable parameter for each attention head to scale the real relative position between time frames, which learns the different preferences on short- or long-term dependencies of these heads. The results demonstrate that our proposal exhibits excellent length generalization ability with comparable or superior performance than other state-of-the-art positional encoding strategies.

Towards Energy-Efficient and Low-Latency Voice-Controlled Smart Homes: A Proposal for Offline Speech Recognition and IoT Integration

The smart home systems, based on AI speech recognition and IoT technology, enable people to control devices through verbal commands and make people's lives more efficient. However, existing AI speech recognition services are primarily deployed on cloud platforms on the Internet. When users issue a command, speech recognition devices like ``Amazon Echo'' will post a recording through numerous network nodes, reach multiple servers, and then receive responses through the Internet. This mechanism presents several issues, including unnecessary energy consumption, communication latency, and the risk of a single-point failure. In this position paper, we propose a smart home concept based on offline speech recognition and IoT technology: 1) integrating offline keyword spotting (KWS) technologies into household appliances with limited resource hardware to enable them to understand user voice commands; 2) designing a local IoT network with decentralized architecture to manage and connect various devices, enhancing the robustness and scalability of the system. This proposal of a smart home based on offline speech recognition and IoT technology will allow users to use low-latency voice control anywhere in the home without depending on the Internet and provide better scalability and energy sustainability.

Technical Report: A Practical Guide to Kaldi ASR Optimization

This technical report introduces innovative optimizations for Kaldi-based Automatic Speech Recognition (ASR) systems, focusing on acoustic model enhancement, hyperparameter tuning, and language model efficiency. We developed a custom Conformer block integrated with a multistream TDNN-F structure, enabling superior feature extraction and temporal modeling. Our approach includes advanced data augmentation techniques and dynamic hyperparameter optimization to boost performance and reduce overfitting. Additionally, we propose robust strategies for language model management, employing Bayesian optimization and $n$-gram pruning to ensure relevance and computational efficiency. These systematic improvements significantly elevate ASR accuracy and robustness, outperforming existing methods and offering a scalable solution for diverse speech recognition scenarios. This report underscores the importance of strategic optimizations in maintaining Kaldi's adaptability and competitiveness in rapidly evolving technological landscapes.

Swiss Parliaments Corpus Re-Imagined (SPC_R): Enhanced Transcription with RAG-based Correction and Predicted BLEU

This paper presents a new long-form release of the Swiss Parliaments Corpus, converting entire multi-hour Swiss German debate sessions (each aligned with the official session protocols) into high-quality speech-text pairs. Our pipeline starts by transcribing all session audio into Standard German using Whisper Large-v3 under high-compute settings. We then apply a two-step GPT-4o correction process: first, GPT-4o ingests the raw Whisper output alongside the official protocols to refine misrecognitions, mainly named entities. Second, a separate GPT-4o pass evaluates each refined segment for semantic completeness. We filter out any segments whose Predicted BLEU score (derived from Whisper's average token log-probability) and GPT-4o evaluation score fall below a certain threshold. The final corpus contains 801 hours of audio, of which 751 hours pass our quality control. Compared to the original sentence-level SPC release, our long-form dataset achieves a 6-point BLEU improvement, demonstrating the power of combining robust ASR, LLM-based correction, and data-driven filtering for low-resource, domain-specific speech corpora.

Cracking the Code: Enhancing Implicit Hate Speech Detection through Coding Classification

The internet has become a hotspot for hate speech (HS), threatening societal harmony and individual well-being. While automatic detection methods perform well in identifying explicit hate speech (ex-HS), they struggle with more subtle forms, such as implicit hate speech (im-HS). We tackle this problem by introducing a new taxonomy for im-HS detection, defining six encoding strategies named codetypes. We present two methods for integrating codetypes into im-HS detection: 1) prompting large language models (LLMs) directly to classify sentences based on generated responses, and 2) using LLMs as encoders with codetypes embedded during the encoding process. Experiments show that the use of codetypes improves im-HS detection in both Chinese and English datasets, validating the effectiveness of our approach across different languages.

French Listening Tests for the Assessment of Intelligibility, Quality, and Identity of Body-Conducted Speech Enhancement

This study evaluates the Extreme Bandwidth Extension Network (EBEN) model on body-conduction sensors through listening tests. Using the Vibravox dataset, we assess intelligibility with a French Modified Rhyme Test, speech quality with a MUSHRA (MUltiple Stimuli with Hidden Reference and Anchor) protocol and speaker identity preservation with an A/B identification task. The experiments involved male and female speakers recorded with a forehead accelerometer, rigid in-ear and throat microphones. The results confirm that EBEN enhances both speech quality and intelligibility. It slightly degrades speaker identification performance when applied to female speakers' throat microphone recordings. The findings also demonstrate a correlation between Short-Time Objective Intelligibility (STOI) and perceived quality in body-conducted speech, while speaker verification using ECAPA2-TDNN aligns well with identification performance. No tested metric reliably predicts EBEN's effect on intelligibility.

LitMAS: A Lightweight and Generalized Multi-Modal Anti-Spoofing Framework for Biometric Security

Biometric authentication systems are increasingly being deployed in critical applications, but they remain susceptible to spoofing. Since most of the research efforts focus on modality-specific anti-spoofing techniques, building a unified, resource-efficient solution across multiple biometric modalities remains a challenge. To address this, we propose LitMAS, a $\textbf{Li}$gh$\textbf{t}$ weight and generalizable $\textbf{M}$ulti-modal $\textbf{A}$nti-$\textbf{S}$poofing framework designed to detect spoofing attacks in speech, face, iris, and fingerprint-based biometric systems. At the core of LitMAS is a Modality-Aligned Concentration Loss, which enhances inter-class separability while preserving cross-modal consistency and enabling robust spoof detection across diverse biometric traits. With just 6M parameters, LitMAS surpasses state-of-the-art methods by $1.36\%$ in average EER across seven datasets, demonstrating high efficiency, strong generalizability, and suitability for edge deployment. Code and trained models are available at https://github.com/IAB-IITJ/LitMAS.

Hybrid Vision Transformer-Mamba Framework for Autism Diagnosis via Eye-Tracking Analysis

Accurate Autism Spectrum Disorder (ASD) diagnosis is vital for early intervention. This study presents a hybrid deep learning framework combining Vision Transformers (ViT) and Vision Mamba to detect ASD using eye-tracking data. The model uses attention-based fusion to integrate visual, speech, and facial cues, capturing both spatial and temporal dynamics. Unlike traditional handcrafted methods, it applies state-of-the-art deep learning and explainable AI techniques to enhance diagnostic accuracy and transparency. Tested on the Saliency4ASD dataset, the proposed ViT-Mamba model outperformed existing methods, achieving 0.96 accuracy, 0.95 F1-score, 0.97 sensitivity, and 0.94 specificity. These findings show the model's promise for scalable, interpretable ASD screening, especially in resource-constrained or remote clinical settings where access to expert diagnosis is limited.

LESS: Large Language Model Enhanced Semi-Supervised Learning for Speech Foundational Models

We introduce LESS (Large Language Model Enhanced Semi-supervised Learning), a versatile framework that leverages Large Language Models (LLMs) to correct pseudo labels generated from in-the-wild data. Within the LESS framework, pseudo-labeled text from Automatic Speech Recognition (ASR) or Automatic Speech Translation (AST) of the unsupervised data is refined by an LLM, and augmented by a data filtering strategy to optimize LLM knowledge transfer efficiency. Experiments on both Mandarin ASR and Spanish-to-English AST tasks show that LESS achieves a notable absolute WER reduction of 3.77% on the Wenet Speech test set, as well as BLEU scores of 34.0 and 64.7 on Callhome and Fisher test sets respectively. These results validate the adaptability of LESS across different languages, tasks, and domains. Ablation studies conducted with various LLMs and prompt configurations provide novel insights into leveraging LLM-derived knowledge for speech processing applications.