{"total":16,"rows":[{"id":"2105.06598","title":"Streaming Transformer for Hardware Efficient Voice Trigger Detection and False Trigger Mitigation","created":"2021-05-14","cited_by_count":8,"area":null},{"id":"2501.19377","title":"SELMA: A Speech-Enabled Language Model for Virtual Assistant Interactions","created":"2025-01-31","cited_by_count":7,"area":null},{"id":"2203.15975","title":"Device-Directed Speech Detection: Regularization via Distillation for Weakly-Supervised Models","created":"2022-03-30","cited_by_count":5,"area":null},{"id":"2312.03632","title":"Multimodal Data and Resource Efficient Device-Directed Speech Detection with Large Foundation Models","created":"2023-12-06","cited_by_count":5,"area":null},{"id":"2403.14438","title":"A Multimodal Approach to Device-Directed Speech Detection with Large Language Models","created":"2024-03-21","cited_by_count":5,"area":null},{"id":"2110.04656","title":"Streaming on-device detection of device directed speech from voice and touch-based invocation","created":"2021-10-09","cited_by_count":4,"area":null},{"id":"2210.12134","title":"Audio-to-Intent Using Acoustic-Textual Subword Representations from End-to-End ASR","created":"2022-10-21","cited_by_count":4,"area":null},{"id":"2310.15261","title":"Modality Dropout for Multimodal Device Directed Speech Detection using Verbal and Non-Verbal Features","created":"2023-10-23","cited_by_count":4,"area":null},{"id":"2208.13322","title":"Streaming Intended Query Detection using E2E Modeling for Continued Conversation","created":"2022-08-29","cited_by_count":3,"area":null},{"id":"2111.10639","title":"Implicit Acoustic Echo Cancellation for Keyword Spotting and Device-Directed Speech Detection","created":"2021-11-20","cited_by_count":2,"area":null},{"id":"2409.09282","title":"Turbo your multi-modal classification with contrastive learning","created":"2024-09-14","cited_by_count":2,"area":null},{"id":"2211.13280","title":"Device Directedness with Contextual Cues for Spoken Dialog Systems","created":"2022-11-23","cited_by_count":1,"area":null},{"id":"2308.07395","title":"Text Injection for Capitalization and Turn-Taking Prediction in Speech Models","created":"2023-08-14","cited_by_count":1,"area":null},{"id":"2411.00023","title":"Device-Directed Speech Detection for Follow-up Conversations Using Large Language Models","created":"2024-10-28","cited_by_count":1,"area":null},{"id":"2604.08412","title":"Selective Attention System (SAS): Device-Addressed Speech Detection for Real-Time On-Device Voice AI","created":"2026-04-09","cited_by_count":0,"area":null},{"id":"2609.12469","title":"Not All Speech Is Intent: Adaptive Self-Correcting Inference Layer for Post-ASR False Wake-Up","created":"2026-09-11","cited_by_count":0,"area":null}],"next_cursor":null}