Investigating End-to-end ASR Architectures For Long Form Audio Transcription

Abstract

This paper presents an overview and evaluation of some of the end-to-end ASR models on long-form audios. We study three categories of Automatic Speech Recognition(ASR) models based on their core architecture: (1) convolutional, (2) convolutional with squeeze-and-excitation and (3) convolutional models with attention. We selected one ASR model from each category and evaluated Word Error Rate, maximum audio length and real-time factor for each model on a variety of long audio benchmarks: Earnings-21 and 22, CORAAL, and TED-LIUM3. The model from the category of self-attention with local attention and global token has the best accuracy comparing to other architectures. We also compared models with CTC and RNNT decoders and showed that CTC-based models are more robust and efficient than RNNT on long form audio.

Stats

• citations6
• S2 citations—
• github stars0
• HF likes0
• heat score6.34
• arxiv keykoluguri2023investigating

Related papers

• A Comparison Of End-to-end Models For Long-form Speech Recognition (2019)12.93
• Recognizing Long-form Speech Using Streaming End-to-end Models (2019)13.74
• Advanced Long-context End-to-end Speech Recognition Using Context-expanded Transformers (2021)10.07
• Audio-attention Discriminative Language Model For ASR Rescoring (2019)9.23
• Improving Non-autoregressive End-to-end Speech Recognition With Pre-trained Acoustic And Language Models (2022)10.07
• Survey Of End-to-end Multi-speaker Automatic Speech Recognition For Monaural Audio (2025)2.26
• 4D ASR: Joint Modeling Of CTC, Attention, Transducer, And Mask-predict Decoders (2022)7.50
• A Comparative Study On Neural Architectures And Training Methods For Japanese Speech Recognition (2021)7.50