Improving Practical Aspects of End-to-End Multi-Talker Speech Recognition for Online and Offline Scenarios

We extend the frameworks of Serialized Output Training (SOT) to address practical needs of both streaming and offline automatic speech recognition (ASR) applications. Our approach focuses on balancing latency and accuracy, catering to real-time captioning and summarization requirements. We propose several key improvements: (1) Leveraging Continuous Speech Separation (CSS) single-channel front-end with end-to-end (E2E) systems for highly overlapping scenarios, challenging the conventional wisdom of E2E versus cascaded setups. The CSS framework improves the accuracy of the ASR system by separating overlapped speech from multiple speakers. (2) Implementing dual models -- Conformer Transducer for streaming and Sequence-to-Sequence for offline -- or alternatively, a two-pass model based on cascaded encoders. (3) Exploring segment-based SOT (segSOT) which is better suited for offline scenarios while also enhancing readability of multi-talker transcriptions.

MambAttention: Mamba with Multi-Head Attention for Generalizable Single-Channel Speech Enhancement

With the advent of new sequence models like Mamba and xLSTM, several studies have shown that these models match or outperform state-of-the-art models in single-channel speech enhancement, automatic speech recognition, and self-supervised audio representation learning. However, prior research has demonstrated that sequence models like LSTM and Mamba tend to overfit to the training set. To address this issue, previous works have shown that adding self-attention to LSTMs substantially improves generalization performance for single-channel speech enhancement. Nevertheless, neither the concept of hybrid Mamba and time-frequency attention models nor their generalization performance have been explored for speech enhancement. In this paper, we propose a novel hybrid architecture, MambAttention, which combines Mamba and shared time- and frequency-multi-head attention modules for generalizable single-channel speech enhancement. To train our model, we introduce VoiceBank+Demand Extended (VB-DemandEx), a dataset inspired by VoiceBank+Demand but with more challenging noise types and lower signal-to-noise ratios. Trained on VB-DemandEx, our proposed MambAttention model significantly outperforms existing state-of-the-art LSTM-, xLSTM-, Mamba-, and Conformer-based systems of similar complexity across all reported metrics on two out-of-domain datasets: DNS 2020 and EARS-WHAM_v2, while matching their performance on the in-domain dataset VB-DemandEx. Ablation studies highlight the role of weight sharing between the time- and frequency-multi-head attention modules for generalization performance. Finally, we explore integrating the shared time- and frequency-multi-head attention modules with LSTM and xLSTM, which yields a notable performance improvement on the out-of-domain datasets. However, our MambAttention model remains superior on both out-of-domain datasets across all reported evaluation metrics.

An accurate and revised version of optical character recognition-based speech synthesis using LabVIEW

Knowledge extraction through sound is a distinctive property. Visually impaired individuals often rely solely on Braille books and audio recordings provided by NGOs. Due to limitations in these approaches, blind individuals often cannot access books of their choice. Speech is a more effective mode of communication than text for blind and visually impaired persons, as they can easily respond to sounds. This paper presents the development of an accurate, reliable, cost-effective, and user-friendly optical character recognition (OCR)-based speech synthesis system. The OCR-based system has been implemented using Laboratory Virtual Instrument Engineering Workbench (LabVIEW).

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.

Adapting Whisper for Streaming Speech Recognition via Two-Pass Decoding

OpenAI Whisper is a family of robust Automatic Speech Recognition (ASR) models trained on 680,000 hours of audio. However, its encoder-decoder architecture, trained with a sequence-to-sequence objective, lacks native support for streaming ASR. In this paper, we fine-tune Whisper for streaming ASR using the WeNet toolkit by adopting a Unified Two-pass (U2) structure. We introduce an additional Connectionist Temporal Classification (CTC) decoder trained with causal attention masks to generate streaming partial transcripts, while the original Whisper decoder reranks these partial outputs. Our experiments on LibriSpeech and an earnings call dataset demonstrate that, with adequate fine-tuning data, Whisper can be adapted into a capable streaming ASR model. We also introduce a hybrid tokenizer approach, which uses a smaller token space for the CTC decoder while retaining Whisper's original token space for the attention decoder, resulting in improved data efficiency and generalization.

Accurate, fast, cheap: Choose three. Replacing Multi-Head-Attention with Bidirectional Recurrent Attention for Long-Form ASR

Long-form speech recognition is an application area of increasing research focus. ASR models based on multi-head attention (MHA) are ill-suited to long-form ASR because of their quadratic complexity in sequence length. We build on recent work that has investigated linear complexity recurrent attention (RA) layers for ASR. We find that bidirectional RA layers can match the accuracy of MHA for both short- and long-form applications. We present a strong limited-context attention (LCA) baseline, and show that RA layers are just as accurate while being more efficient. We develop a long-form training paradigm which further improves RA performance, leading to better accuracy than LCA with 44% higher throughput. We also present Direction Dropout, a novel regularization method that improves accuracy, provides fine-grained control of the accuracy/throughput trade-off of bidirectional RA, and enables a new alternating directions decoding mode with even higher throughput.

Lightweight and Robust Multi-Channel End-to-End Speech Recognition with Spherical Harmonic Transform

This paper presents SHTNet, a lightweight spherical harmonic transform (SHT) based framework, which is designed to address cross-array generalization challenges in multi-channel automatic speech recognition (ASR) through three key innovations. First, SHT based spatial sound field decomposition converts microphone signals into geometry-invariant spherical harmonic coefficients, isolating signal processing from array geometry. Second, the Spatio-Spectral Attention Fusion Network (SSAFN) combines coordinate-aware spatial modeling, refined self-attention channel combinator, and spectral noise suppression without conventional beamforming. Third, Rand-SHT training enhances robustness through random channel selection and array geometry reconstruction. The system achieves 39.26\% average CER across heterogeneous arrays (e.g., circular, square, and binaural) on datasets including Aishell-4, Alimeeting, and XMOS, with 97.1\% fewer computations than conventional neural beamformers.

Regularizing Learnable Feature Extraction for Automatic Speech Recognition

Neural front-ends are an appealing alternative to traditional, fixed feature extraction pipelines for automatic speech recognition (ASR) systems since they can be directly trained to fit the acoustic model. However, their performance often falls short compared to classical methods, which we show is largely due to their increased susceptibility to overfitting. This work therefore investigates regularization methods for training ASR models with learnable feature extraction front-ends. First, we examine audio perturbation methods and show that larger relative improvements can be obtained for learnable features. Additionally, we identify two limitations in the standard use of SpecAugment for these front-ends and propose masking in the short time Fourier transform (STFT)-domain as a simple but effective modification to address these challenges. Finally, integrating both regularization approaches effectively closes the performance gap between traditional and learnable features.

SC-SOT: Conditioning the Decoder on Diarized Speaker Information for End-to-End Overlapped Speech Recognition

We propose Speaker-Conditioned Serialized Output Training (SC-SOT), an enhanced SOT-based training for E2E multi-talker ASR. We first probe how SOT handles overlapped speech, and we found the decoder performs implicit speaker separation. We hypothesize this implicit separation is often insufficient due to ambiguous acoustic cues in overlapping regions. To address this, SC-SOT explicitly conditions the decoder on speaker information, providing detailed information about "who spoke when". Specifically, we enhance the decoder by incorporating: (1) speaker embeddings, which allow the model to focus on the acoustic characteristics of the target speaker, and (2) speaker activity information, which guides the model to suppress non-target speakers. The speaker embeddings are derived from a jointly trained E2E speaker diarization model, mitigating the need for speaker enrollment. Experimental results demonstrate the effectiveness of our conditioning approach on overlapped speech.

FairASR: Fair Audio Contrastive Learning for Automatic Speech Recognition

Large-scale ASR models have achieved remarkable gains in accuracy and robustness. However, fairness issues remain largely unaddressed despite their critical importance in real-world applications. In this work, we introduce FairASR, a system that mitigates demographic bias by learning representations that are uninformative about group membership, enabling fair generalization across demographic groups. Leveraging a multi-demographic dataset, our approach employs a gradient reversal layer to suppress demographic-discriminative features while maintaining the ability to capture generalizable speech patterns through an unsupervised contrastive loss. Experimental results show that FairASR delivers competitive overall ASR performance while significantly reducing performance disparities across different demographic groups.