asr_eval: Algorithms and tools for multi-reference and streaming speech recognition evaluation

We propose several improvements to the speech recognition evaluation. First, we propose a string alignment algorithm that supports both multi-reference labeling, arbitrary-length insertions and better word alignment. This is especially useful for non-Latin languages, those with rich word formation, to label cluttered or longform speech. Secondly, we collect a novel test set DiverseSpeech-Ru of longform in-the-wild Russian speech with careful multi-reference labeling. We also perform multi-reference relabeling of popular Russian tests set and study fine-tuning dynamics on its corresponding train set. We demonstrate that the model often adopts to dataset-specific labeling, causing an illusion of metric improvement. Based on the improved word alignment, we develop tools to evaluate streaming speech recognition and to align multiple transcriptions to compare them visually. Additionally, we provide uniform wrappers for many offline and streaming speech recognition models. Our code will be made publicly available.

MA-LipNet: Multi-Dimensional Attention Networks for Robust Lipreading

Lipreading, the technology of decoding spoken content from silent videos of lip movements, holds significant application value in fields such as public security. However, due to the subtle nature of articulatory gestures, existing lipreading methods often suffer from limited feature discriminability and poor generalization capabilities. To address these challenges, this paper delves into the purification of visual features from temporal, spatial, and channel dimensions. We propose a novel method named Multi-Attention Lipreading Network(MA-LipNet). The core of MA-LipNet lies in its sequential application of three dedicated attention modules. Firstly, a \textit{Channel Attention (CA)} module is employed to adaptively recalibrate channel-wise features, thereby mitigating interference from less informative channels. Subsequently, two spatio-temporal attention modules with distinct granularities-\textit{Joint Spatial-Temporal Attention (JSTA)} and \textit{Separate Spatial-Temporal Attention (SSTA)}-are leveraged to suppress the influence of irrelevant pixels and video frames. The JSTA module performs a coarse-grained filtering by computing a unified weight map across the spatio-temporal dimensions, while the SSTA module conducts a more fine-grained refinement by separately modeling temporal and spatial attentions. Extensive experiments conducted on the CMLR and GRID datasets demonstrate that MA-LipNet significantly reduces the Character Error Rate (CER) and Word Error Rate (WER), validating its effectiveness and superiority over several state-of-the-art methods. Our work highlights the importance of multi-dimensional feature refinement for robust visual speech recognition.

OCR-Enhanced Multimodal ASR Can Read While Listening

Visual information, such as subtitles in a movie, often helps automatic speech recognition. In this paper, we propose Donut-Whisper, an audio-visual ASR model with dual encoder to leverage visual information to improve speech recognition performance in both English and Chinese. Donut-Whisper combines the advantage of the linear and the Q-Former-based modality alignment structures via a cross-attention module, generating more powerful audio-visual features. Meanwhile, we propose a lightweight knowledge distillation scheme showcasing the potential of using audio-visual models to teach audio-only models to achieve better performance. Moreover, we propose a new multilingual audio-visual speech recognition dataset based on movie clips containing both Chinese and English partitions. As a result, Donut-Whisper achieved significantly better performance on both English and Chinese partition of the dataset compared to both Donut and Whisper large V3 baselines. In particular, an absolute 5.75% WER reduction and a 16.5% absolute CER reduction were achieved on the English and Chinese sets respectively compared to the Whisper ASR baseline.

Noise-Robust AV-ASR Using Visual Features Both in the Whisper Encoder and Decoder

In audiovisual automatic speech recognition (AV-ASR) systems, information fusion of visual features in a pre-trained ASR has been proven as a promising method to improve noise robustness. In this work, based on the prominent Whisper ASR, first, we propose a simple and effective visual fusion method -- use of visual features both in encoder and decoder (dual-use) -- to learn the audiovisual interactions in the encoder and to weigh modalities in the decoder. Second, we compare visual fusion methods in Whisper models of various sizes. Our proposed dual-use method shows consistent noise robustness improvement, e.g., a 35% relative improvement (WER: 4.41% vs. 6.83%) based on Whisper small, and a 57% relative improvement (WER: 4.07% vs. 9.53%) based on Whisper medium, compared to typical reference middle fusion in babble noise with a signal-to-noise ratio (SNR) of 0dB. Third, we conduct ablation studies examining the impact of various module designs and fusion options. Fine-tuned on 1929 hours of audiovisual data, our dual-use method using Whisper medium achieves 4.08% (MUSAN babble noise) and 4.43% (NoiseX babble noise) average WER across various SNRs, thereby establishing a new state-of-the-art in noisy conditions on the LRS3 AV-ASR benchmark. Our code is at https://github.com/ifnspaml/Dual-Use-AVASR

Purification Before Fusion: Toward Mask-Free Speech Enhancement for Robust Audio-Visual Speech Recognition

Audio-visual speech recognition (AVSR) typically improves recognition accuracy in noisy environments by integrating noise-immune visual cues with audio signals. Nevertheless, high-noise audio inputs are prone to introducing adverse interference into the feature fusion process. To mitigate this, recent AVSR methods often adopt mask-based strategies to filter audio noise during feature interaction and fusion, yet such methods risk discarding semantically relevant information alongside noise. In this work, we propose an end-to-end noise-robust AVSR framework coupled with speech enhancement, eliminating the need for explicit noise mask generation. This framework leverages a Conformer-based bottleneck fusion module to implicitly refine noisy audio features with video assistance. By reducing modality redundancy and enhancing inter-modal interactions, our method preserves speech semantic integrity to achieve robust recognition performance. Experimental evaluations on the public LRS3 benchmark suggest that our method outperforms prior advanced mask-based baselines under noisy conditions.

HoverAI: An Embodied Aerial Agent for Natural Human-Drone Interaction

Drones operating in human-occupied spaces suffer from insufficient communication mechanisms that create uncertainty about their intentions. We present HoverAI, an embodied aerial agent that integrates drone mobility, infrastructure-independent visual projection, and real-time conversational AI into a unified platform. Equipped with a MEMS laser projector, onboard semi-rigid screen, and RGB camera, HoverAI perceives users through vision and voice, responding via lip-synced avatars that adapt appearance to user demographics. The system employs a multimodal pipeline combining VAD, ASR (Whisper), LLM-based intent classification, RAG for dialogue, face analysis for personalization, and voice synthesis (XTTS v2). Evaluation demonstrates high accuracy in command recognition (F1: 0.90), demographic estimation (gender F1: 0.89, age MAE: 5.14 years), and speech transcription (WER: 0.181). By uniting aerial robotics with adaptive conversational AI and self-contained visual output, HoverAI introduces a new class of spatially-aware, socially responsive embodied agents for applications in guidance, assistance, and human-centered interaction.

AI-based System for Transforming text and sound to Educational Videos

Technological developments have produced methods that can generate educational videos from input text or sound. Recently, the use of deep learning techniques for image and video generation has been widely explored, particularly in education. However, generating video content from conditional inputs such as text or speech remains a challenging area. In this paper, we introduce a novel method to the educational structure, Generative Adversarial Network (GAN), which develop frame-for-frame frameworks and are able to create full educational videos. The proposed system is structured into three main phases In the first phase, the input (either text or speech) is transcribed using speech recognition. In the second phase, key terms are extracted and relevant images are generated using advanced models such as CLIP and diffusion models to enhance visual quality and semantic alignment. In the final phase, the generated images are synthesized into a video format, integrated with either pre-recorded or synthesized sound, resulting in a fully interactive educational video. The proposed system is compared with other systems such as TGAN, MoCoGAN, and TGANS-C, achieving a Fréchet Inception Distance (FID) score of 28.75%, which indicates improved visual quality and better over existing methods.

Robust CAPTCHA Using Audio Illusions in the Era of Large Language Models: from Evaluation to Advances

CAPTCHAs are widely used by websites to block bots and spam by presenting challenges that are easy for humans but difficult for automated programs to solve. To improve accessibility, audio CAPTCHAs are designed to complement visual ones. However, the robustness of audio CAPTCHAs against advanced Large Audio Language Models (LALMs) and Automatic Speech Recognition (ASR) models remains unclear. In this paper, we introduce AI-CAPTCHA, a unified framework that offers (i) an evaluation framework, ACEval, which includes advanced LALM- and ASR-based solvers, and (ii) a novel audio CAPTCHA approach, IllusionAudio, leveraging audio illusions. Through extensive evaluations of seven widely deployed audio CAPTCHAs, we show that most existing methods can be solved with high success rates by advanced LALMs and ASR models, exposing critical security weaknesses. To address these vulnerabilities, we design a new audio CAPTCHA approach, IllusionAudio, which exploits perceptual illusion cues rooted in human auditory mechanisms. Extensive experiments demonstrate that our method defeats all tested LALM- and ASR-based attacks while achieving a 100% human pass rate, significantly outperforming existing audio CAPTCHA methods.

MCGA: A Multi-task Classical Chinese Literary Genre Audio Corpus

With the rapid advancement of Multimodal Large Language Models (MLLMs), their potential has garnered significant attention in Chinese Classical Studies (CCS). While existing research has primarily focused on text and visual modalities, the audio corpus within this domain remains largely underexplored. To bridge this gap, we propose the Multi-task Classical Chinese Literary Genre Audio Corpus (MCGA). It encompasses a diverse range of literary genres across six tasks: Automatic Speech Recognition (ASR), Speech-to-Text Translation (S2TT), Speech Emotion Captioning (SEC), Spoken Question Answering (SQA), Speech Understanding (SU), and Speech Reasoning (SR). Through the evaluation of ten MLLMs, our experimental results demonstrate that current models still face substantial challenges when processed on the MCGA test set. Furthermore, we introduce an evaluation metric for SEC and a metric to measure the consistency between the speech and text capabilities of MLLMs. We release MCGA and our code to the public to facilitate the development of MLLMs with more robust multidimensional audio capabilities in CCS. MCGA Corpus: https://github.com/yxduir/MCGA

VALLR-Pin: Uncertainty-Factorized Visual Speech Recognition for Mandarin with Pinyin Guidance

Visual speech recognition (VSR) aims to transcribe spoken content from silent lip-motion videos and is particularly challenging in Mandarin due to severe viseme ambiguity and pervasive homophones. We propose VALLR-Pin, a two-stage Mandarin VSR framework that extends the VALLR architecture by explicitly incorporating Pinyin as an intermediate representation. In the first stage, a shared visual encoder feeds dual decoders that jointly predict Mandarin characters and their corresponding Pinyin sequences, encouraging more robust visual-linguistic representations. In the second stage, an LLM-based refinement module takes the predicted Pinyin sequence together with an N-best list of character hypotheses to resolve homophone-induced ambiguities. To further adapt the LLM to visual recognition errors, we fine-tune it on synthetic instruction data constructed from model-generated Pinyin-text pairs, enabling error-aware correction. Experiments on public Mandarin VSR benchmarks demonstrate that VALLR-Pin consistently improves transcription accuracy under multi-speaker conditions, highlighting the effectiveness of combining phonetic guidance with lightweight LLM refinement.