{"work":{"id":"eb57b6c8-18a7-4e51-b90a-2add68d4ee9e","openalex_id":null,"doi":null,"arxiv_id":"1412.5567","raw_key":null,"title":"Deep Speech: Scaling up end-to-end speech recognition","authors":null,"authors_text":"A","year":2014,"venue":"cs.CL","abstract":"We present a state-of-the-art speech recognition system developed using end-to-end deep learning. Our architecture is significantly simpler than traditional speech systems, which rely on laboriously engineered processing pipelines; these traditional systems also tend to perform poorly when used in noisy environments. In contrast, our system does not need hand-designed components to model background noise, reverberation, or speaker variation, but instead directly learns a function that is robust to such effects. We do not need a phoneme dictionary, nor even the concept of a \"phoneme.\" Key to our approach is a well-optimized RNN training system that uses multiple GPUs, as well as a set of novel data synthesis techniques that allow us to efficiently obtain a large amount of varied data for training. Our system, called Deep Speech, outperforms previously published results on the widely studied Switchboard Hub5'00, achieving 16.0% error on the full test set. Deep Speech also handles challenging noisy environments better than widely used, state-of-the-art commercial speech systems.","external_url":"https://arxiv.org/abs/1412.5567","cited_by_count":null,"metadata_source":"pith","metadata_fetched_at":"2026-05-25T15:05:57.752025+00:00","pith_arxiv_id":"1412.5567","created_at":"2026-05-10T00:39:48.465488+00:00","updated_at":"2026-05-25T15:05:57.752025+00:00","title_quality_ok":true,"display_title":"Hannun, C","render_title":"Hannun, C"},"hub":{"state":{"work_id":"eb57b6c8-18a7-4e51-b90a-2add68d4ee9e","tier":"hub","tier_reason":"10+ Pith inbound or 1,000+ external citations","pith_inbound_count":12,"external_cited_by_count":null,"distinct_field_count":7,"first_pith_cited_at":"2017-10-10T17:42:04+00:00","last_pith_cited_at":"2026-04-22T17:59:58+00:00","author_build_status":"not_needed","summary_status":"needed","contexts_status":"needed","graph_status":"needed","ask_index_status":"not_needed","reader_status":"not_needed","recognition_status":"not_needed","updated_at":"2026-05-29T22:50:37.760961+00:00","tier_text":"hub"},"tier":"hub","role_counts":[{"context_role":"background","n":2},{"context_role":"dataset","n":1}],"polarity_counts":[{"context_polarity":"background","n":2},{"context_polarity":"use_dataset","n":1}],"runs":{},"summary":{},"graph":{},"authors":[]}}