Toward Low-Latency End-to-End Voice Agents for Telecommunications Using Streaming ASR, Quantized LLMs, and Real-Time TTS

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Ethiraj, Vignesh, David, Ashwath, Menon, Sidhanth, Vijay, Divya
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909726354178048
author Ethiraj, Vignesh
David, Ashwath
Menon, Sidhanth
Vijay, Divya
author_facet Ethiraj, Vignesh
David, Ashwath
Menon, Sidhanth
Vijay, Divya
contents We introduce a low-latency telecom AI voice agent pipeline for real-time, interactive telecommunications use, enabling advanced voice AI for call center automation, intelligent IVR (Interactive Voice Response), and AI-driven customer support. The solution is built for telecom, combining four specialized models by NetoAI: TSLAM, a 4-bit quantized Telecom-Specific Large Language Model (LLM); T-VEC, a Telecom-Specific Embedding Model; TTE, a Telecom-Specific Automatic Speech Recognition (ASR) model; and T-Synth, a Telecom-Specific Text-to-Speech (TTS) model. These models enable highly responsive, domain-adapted voice AI agents supporting knowledge-grounded spoken interactions with low latency. The pipeline integrates streaming ASR (TTE), conversational intelligence (TSLAM), retrieval augmented generation (RAG) over telecom documents, and real-time TTS (T-Synth), setting a new benchmark for telecom voice assistants. To evaluate the system, we built a dataset of 500 human-recorded telecom questions from RFCs, simulating real telecom agent queries. This framework allows analysis of latency, domain relevance, and real-time performance across the stack. Results show that TSLAM, TTE, and T-Synth deliver real-time factors (RTF) below 1.0, supporting enterprise, low-latency telecom deployments. These AI agents -- powered by TSLAM, TTE, and T-Synth -- provide a foundation for next-generation telecom AI, enabling automated customer support, diagnostics, and more.
format Preprint
id arxiv_https___arxiv_org_abs_2508_04721
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Toward Low-Latency End-to-End Voice Agents for Telecommunications Using Streaming ASR, Quantized LLMs, and Real-Time TTS
Ethiraj, Vignesh
David, Ashwath
Menon, Sidhanth
Vijay, Divya
Sound
Artificial Intelligence
Audio and Speech Processing
68T50, 68T10, 94A12
I.2.7; H.3.3; C.2.2
We introduce a low-latency telecom AI voice agent pipeline for real-time, interactive telecommunications use, enabling advanced voice AI for call center automation, intelligent IVR (Interactive Voice Response), and AI-driven customer support. The solution is built for telecom, combining four specialized models by NetoAI: TSLAM, a 4-bit quantized Telecom-Specific Large Language Model (LLM); T-VEC, a Telecom-Specific Embedding Model; TTE, a Telecom-Specific Automatic Speech Recognition (ASR) model; and T-Synth, a Telecom-Specific Text-to-Speech (TTS) model. These models enable highly responsive, domain-adapted voice AI agents supporting knowledge-grounded spoken interactions with low latency. The pipeline integrates streaming ASR (TTE), conversational intelligence (TSLAM), retrieval augmented generation (RAG) over telecom documents, and real-time TTS (T-Synth), setting a new benchmark for telecom voice assistants. To evaluate the system, we built a dataset of 500 human-recorded telecom questions from RFCs, simulating real telecom agent queries. This framework allows analysis of latency, domain relevance, and real-time performance across the stack. Results show that TSLAM, TTE, and T-Synth deliver real-time factors (RTF) below 1.0, supporting enterprise, low-latency telecom deployments. These AI agents -- powered by TSLAM, TTE, and T-Synth -- provide a foundation for next-generation telecom AI, enabling automated customer support, diagnostics, and more.
title Toward Low-Latency End-to-End Voice Agents for Telecommunications Using Streaming ASR, Quantized LLMs, and Real-Time TTS
topic Sound
Artificial Intelligence
Audio and Speech Processing
68T50, 68T10, 94A12
I.2.7; H.3.3; C.2.2
url https://arxiv.org/abs/2508.04721