# Semantic Segmentation with Bidirectional Language Models Improves Long-form ASR Source: [Semantic Segmentation with Bidirectional Language Models Improves Long-form ASR]() Collection index: [llms.txt]() Data updated: 2025-10-26T01:23:24.960Z Authors: W. Ronny Huang, Hao Zhang, Shankar Kumar, Shuo-yiin Chang, Tara N. Sainath Published: 2023-05-28T19:31:45.000Z ## Abstract We propose a method of segmenting long-form speech by separating semantically complete sentences within the utterance. This prevents the ASR decoder from needlessly processing faraway context while also preventing it from missing relevant context within the current sentence. Semantically complete sentence boundaries are typically demarcated by punctuation in written text; but unfortunately, spoken real-world utterances rarely contain punctuation. We address this limitation by distilling punctuation knowledge from a bidirectional teacher language model (LM) trained on written, punctuated text. We compare our segmenter, which is distilled from the LM teacher, against a segmenter distilled from a acoustic-pause-based teacher used in other works, on a streaming ASR pipeline. The pipeline with our segmenter achieves a 3.2% relative WER gain along with a 60 ms median end-of-segment latency reduction on a YouTube captioning task. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. ## Original sources and implementation [Original paper]() [PDF]()