Real-Time Voicemail Detection in Telephony Audio Using Temporal Speech Activity Features

• URL: http://arxiv.org/abs/2604.09675v1
• Date: Thu, 02 Apr 2026 17:43:24 GMT
• Title: Real-Time Voicemail Detection in Telephony Audio Using Temporal Speech Activity Features
• Abstract summary: We present a lightweight approach that extracts 15 temporal features from the speech activity pattern of a pre-trained neural voice activity detector.<n>Across two evaluation sets totaling 764 telephony recordings, the system achieves a combined 96.1% accuracy.
• Score: 1.066048003460524
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Outbound AI calling systems must distinguish voicemail greetings from live human answers in real time to avoid wasted agent interactions and dropped calls. We present a lightweight approach that extracts 15 temporal features from the speech activity pattern of a pre-trained neural voice activity detector (VAD), then classifies with a shallow tree-based ensemble. Across two evaluation sets totaling 764 telephony recordings, the system achieves a combined 96.1% accuracy (734/764), with 99.3% (139/140) on an expert-labeled test set and 95.4% (595/624) on a held-out production set. In production validation over 77,000 calls, it maintained a 0.3% false positive rate and 1.3% false negative rate. End-to-end inference completes in 46 ms on a commodity dual-core CPU with no GPU, supporting 380+ concurrent WebSocket calls. In our search over 3,780 model, feature, and threshold combinations, feature importance was concentrated in three temporal variables. Adding transcription keywords or beep-based features did not improve the best real-time configuration and increased latency substantially. Our results suggest that temporal speech patterns are a strong signal for distinguishing voicemail greetings from live human answers.

Related papers

• Realtime-Venus: A full-duplex interaction system with asynchronous delegation [59.69745588222872]
  We present Realtime, Realtime Omni audio visual interaction and Realtime-Audio Spoken for spoken interaction.<n>Each model serves as complete conversational, integrating continuous perception, conversational control, and native speech generation.
  arXiv  Detail & Related papers  (2026-09-12T08:56:50Z)
• The Machines Are Calling: Measuring Automated and Synthetic Voices in Unwanted Inbound Calls [8.497127814945147]
  In 2024 the FCC placed AI-generated voices under the Telephone Consumer Protection Act ( TCPA)<n>No peer-reviewed measurement says how much unwanted call traffic is placed by a machine.<n>An interactive voice honeypot recorded 10,987 calls over 66 days.
  arXiv  Detail & Related papers  (2026-09-10T06:28:50Z)
• TurnBench: A Multi-Domain Benchmark for Turn-Taking Dynamics in Spoken Dialogue [79.83228182492354]
  Speakers in natural conversation take turns speaking and listening, deciding in real time when to take, hold, or yield the floor.<n>We present TurnBench, a benchmark that pairs a 30-hour, hand-labeled corpus of dyadic human conversation with a standardized evaluation protocol for end-of-turn and interruption detection.<n>We find end-of-turn recall stable across types, while interruption false positives are strongly type-dependent and concentrated in backchannel-dense interaction styles.
  arXiv  Detail & Related papers  (2026-08-25T23:14:36Z)
• EmotionAI: A Privacy-Preserving Computational Intelligence Pipeline for Speech-Emotion-Grounded Conversational Analysis [1.5803208833562954]
  EmotionAI is a fully local Computational Intelligence pipeline that couples Speech Emotion Recognition with generative reasoning.<n>Speaker diarisation, Whisper Automatic Speech Recognition (ASR) and a wav2vec2 emotion classifier produce per-segment affective evidence.<n>The contribution is not state-of-the-art SER but an auditable, privacy-preserving integration of imperfect affective evidence into grounded conversational analysis.
  arXiv  Detail & Related papers  (2026-06-22T20:45:49Z)
• Enhancing Speaker Verification with Whispered Speech via Post-Processing [1.8849814100256281]
  We propose a model with a training recipe to obtain more robust representations against whispered speech hindrances.<n>The proposed system employs an encoder--decoder structure built atop a fine-tuned speaker verification backbone.<n>We also offer a summary of the most popular and state-of-the-art speaker verification models in terms of their performance with whispered speech.
  arXiv  Detail & Related papers  (2026-04-22T06:23:40Z)
• iPhoneme: Brain-to-Text Communication for ALS Using ConformerXL Decoding [1.529342790344802]
  We present iPhoneme, a brain-to-text communication system for ALS patients.<n>The system combines a deep learning phoneme decoder with a gaze-assisted phoneme input interface.<n>On the interaction side, iPhoneme introduces a chorded gaze-plus-silent-speech paradigm that replaces dwell-time selection.
  arXiv  Detail & Related papers  (2026-04-07T05:08:27Z)
• A Hierarchical End-of-Turn Model with Primary Speaker Segmentation for Real-Time Conversational AI [3.995809098639418]
  We present a real-time front-end for voice-based conversational AI to enable natural turn-taking in two-speaker scenarios.<n>To operate robustly in multi-speaker environments, the system continuously identifies and tracks the primary user.
  arXiv  Detail & Related papers  (2026-03-10T21:17:17Z)
• Predictive Speech Recognition and End-of-Utterance Detection Towards Spoken Dialog Systems [55.99999020778169]
  We study a function that can predict the forthcoming words and estimate the time remaining until the end of an utterance. We develop a cross-attention-based algorithm that incorporates both acoustic and linguistic information. Results demonstrate the proposed model's ability to predict upcoming words and estimate future EOU events up to 300ms prior to the actual EOU.
  arXiv  Detail & Related papers  (2024-09-30T06:29:58Z)
• Robust Wake-Up Word Detection by Two-stage Multi-resolution Ensembles [48.208214762257136]
  It employs two models: a lightweight on-device model for real-time processing of the audio stream and a verification model on the server-side. To protect privacy, audio features are sent to the cloud instead of raw audio.
  arXiv  Detail & Related papers  (2023-10-17T16:22:18Z)
• Decoding speech perception from non-invasive brain recordings [48.46819575538446]
  We introduce a model trained with contrastive-learning to decode self-supervised representations of perceived speech from non-invasive recordings. Our model can identify, from 3 seconds of MEG signals, the corresponding speech segment with up to 41% accuracy out of more than 1,000 distinct possibilities.
  arXiv  Detail & Related papers  (2022-08-25T10:01:43Z)
• SuperVoice: Text-Independent Speaker Verification Using Ultrasound Energy in Human Speech [10.354590276508283]
  Voice-activated systems are integrated into a variety of desktop, mobile, and Internet-of-Things (IoT) devices. Existing speaker verification techniques distinguish individual speakers via the spectrographic features extracted from an audible frequency range of voice commands. We propose a speaker verification system, SUPERVOICE, that uses a two-stream architecture with a feature fusion mechanism to generate distinctive speaker models.
  arXiv  Detail & Related papers  (2022-05-28T18:00:50Z)
• On the pragmatism of using binary classifiers over data intensive neural network classifiers for detection of COVID-19 from voice [34.553128768223615]
  We show that detecting COVID-19 from voice does not require custom-made non-standard features or complicated neural network classifiers. We demonstrate this from a human-curated dataset collected and calibrated in clinical settings.
  arXiv  Detail & Related papers  (2022-04-11T00:19:14Z)
• Nonverbal Sound Detection for Disordered Speech [24.636175845214822]
  We introduce an alternative voice-based input system which relies on sound event detection using fifteen non-verbal mouth sounds. This system was designed to work regardless of ones' speech abilities and allows full access to existing technology.
  arXiv  Detail & Related papers  (2022-02-15T22:02:58Z)
• Real-time Speaker counting in a cocktail party scenario using Attention-guided Convolutional Neural Network [60.99112031408449]
  We propose a real-time, single-channel attention-guided Convolutional Neural Network (CNN) to estimate the number of active speakers in overlapping speech. The proposed system extracts higher-level information from the speech spectral content using a CNN model. Experiments on simulated overlapping speech using WSJ corpus show that the attention solution is shown to improve the performance by almost 3% absolute over conventional temporal average pooling.
  arXiv  Detail & Related papers  (2021-10-30T19:24:57Z)
• HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units [81.53783563025084]
  We propose an offline clustering step to provide aligned target labels for a BERT-like prediction loss. A key ingredient of our approach is applying the prediction loss over the masked regions only. HuBERT shows up to 19% and 13% relative WER reduction on the more challenging dev-other and test-other evaluation subsets.
  arXiv  Detail & Related papers  (2021-06-14T14:14:28Z)
• Any-to-Many Voice Conversion with Location-Relative Sequence-to-Sequence Modeling [61.351967629600594]
  This paper proposes an any-to-many location-relative, sequence-to-sequence (seq2seq), non-parallel voice conversion approach. In this approach, we combine a bottle-neck feature extractor (BNE) with a seq2seq synthesis module. Objective and subjective evaluations show that the proposed any-to-many approach has superior voice conversion performance in terms of both naturalness and speaker similarity.
  arXiv  Detail & Related papers  (2020-09-06T13:01:06Z)
• XiaoiceSing: A High-Quality and Integrated Singing Voice Synthesis System [31.283081762312964]
  XiaoiceSing is a singing voice synthesis system which employs an integrated network for spectrum, F0 and duration modeling. Experiment results show that XiaoiceSing outperforms the baseline system of convolutional neural networks by 1.44 MOS on sound quality, 1.18 on pronunciation accuracy and 1.38 on naturalness.
  arXiv  Detail & Related papers  (2020-06-11T09:09:59Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.