This article presents a comprehensive overview of 360's voice interaction platform, detailing dialogue system fundamentals, platform architecture, and core technologies such as semantic understanding, dialog management, and question answering, all driven by deep learning and multimodal innovations.
AINatural Language UnderstandingSpeech Recognition
The article reviews Interspeech 2019, summarizing major trends and representative papers in end‑to‑end speech recognition, synthesis, natural language understanding, speaker recognition, and speech translation, while also highlighting best student papers and providing resources for further study.
This article describes the TPNN deep‑learning platform’s multi‑GPU acceleration, data‑parallel BMUF training, LSTM‑CTC acoustic modeling, and a suite of mobile‑side optimizations—including model pruning, 8‑bit quantization, low‑precision matrix multiplication and mixed‑precision computation—that together achieve over 92% recognition accuracy for children’s English speech on both server and mobile devices.
This article presents a comprehensive overview of modern speech recognition technology, covering basic ASR concepts, classic acoustic and language models, deep‑learning approaches such as DNN‑HMM, CTC, attention‑based and transformer models, multimodal fusion, signal‑processing pipelines, and practical deployment considerations at Didi.
Microsoft appointed its first Chinese Global Technical Fellow, Huang Xuedong, as the company’s Global AI CTO, overseeing Azure’s speech, translation, vision, and language services, while highlighting his groundbreaking achievements such as achieving human‑level word error rates and leading AI research teams.
The talk introduced iQIYI’s HomeAI platform, which combines user profiling (including voiceprint and age detection) with automatic video semantic extraction to enable natural, multi‑turn voice‑based video search—addressing hot‑content updates, contextual awareness, device environments, and personalized recommendations for screen‑less or accessibility‑focused users.
This article presents a complete solution for 58.com’s human‑machine voice dialogue robot, detailing its background, overall architecture, intelligent outbound process, core functions such as call service, anti‑spam, status recognition, multi‑turn dialogue management, intent classification, slot extraction, whole‑round intent detection, and various practical application scenarios.
This article presents the end‑to‑end solution of 58.com’s voice dialogue robot, detailing its overall architecture, intelligent outbound process, core functions such as call dialing, status recognition, dialogue management, intent detection, and showcasing multiple real‑world application scenarios that improve sales, operations, and customer service efficiency.
This article presents a distributed system that efficiently supports large‑scale n‑gram language models for automatic speech recognition by introducing caching, a two‑level distributed index, batch processing, and a cascading fault‑tolerance mechanism, demonstrating robust scalability and low communication overhead in Tencent's WeChat ASR service.
Intelligent speech recognition converts spoken audio to text using a pipeline of feature extraction, acoustic and language modeling, where deep neural networks—especially CNN, LSTM, and hybrid CLDNN architectures—drive high accuracy, enabling mobile voice input, call‑center transcription, legal record keeping, and Tencent Cloud ASR’s 97% Mandarin accuracy with speaker separation and on‑premises deployment.
This article presents a comprehensive overview of an intelligent voice robot's dialogue management system, detailing its architecture, natural language understanding components, dialogue manager design, strategy handling, and workflow processes to achieve fluent multi‑turn interactions in telephone scenarios.
At ACL 2019, Didi unveiled DELTA, an open‑source TensorFlow‑based training framework that unifies NLP and speech tasks, offers configurable pipelines, benchmark models, and seamless deployment, enabling AI developers to quickly move from research to production while leveraging Didi’s extensive open‑source ecosystem.
This article introduces Alibaba's new e‑book collection of five ICASSP‑accepted papers that showcase advances in speech recognition, synthesis, and emotion detection, detailing novel models like DFSMN, A‑LSTM, and speaker‑adaptation techniques that dramatically improve speed, size, and accuracy.
Using AI to automatically understand and secure audio content, this article discusses the challenges of manual audio analysis, outlines a four‑step pipeline—audio segmentation, speech‑to‑text, labeling, and synthesis—and describes models such as VAD, ASR, sound classification, text recognition, and behavior detection for live‑stream moderation.
This article reviews the fundamentals of automatic speech recognition, compares traditional MFCC‑GMM‑HMM pipelines with modern deep neural network approaches such as DNN‑HMM, LSTM‑CTC, and attention‑based models, and illustrates each evolution step with flowchart diagrams and key references.
Tencent Cloud's intelligent speech platform combines high‑accuracy ASR, advanced WaveNet‑based TTS, and solutions for noise, far‑field, and dialect challenges, enabling voice input, transcription, and customer‑service bots, with real‑world deployments in finance, museums, hotels, and other industry scenarios.
This article reviews the development roadmap, current industry status, challenges, typical deployment scenarios, and optimization methods for speech recognition (ASR) and speech synthesis (TTS), and shares several Tencent Cloud intelligent voice case studies to illustrate practical applications.
After the Chinese New Year break, this curated collection of key AI articles—spanning computer vision, speech recognition, natural language processing, recommendation systems, and more—helps technical readers quickly regain momentum in work and study by revisiting core technologies with real‑world case studies.
This guide walks you through the fundamentals of speech recognition, explains how modern systems work, shows how to choose and install the Python SpeechRecognition package, and demonstrates processing audio files, handling noise, using offsets, and capturing live microphone input with practical code examples.
This article presents a comprehensive technical analysis of JD’s Intelligent Customer Service 2.0, detailing AI‑based intent recognition with the ABSQ framework, hierarchical attention networks, emotion analysis via CNN, speech navigation using ASR/NLP, and machine‑learning‑driven smart dispatch that together boost accuracy and user experience.
At the inaugural Tencent Cloud+ Community Developer Conference, experts detailed the evolution of speech and semantic recognition—from early MFCC/HMM‑GMM models to modern end‑to‑end deep‑learning architectures—and showcased WeChat Zhiling’s full‑stack platform, multilingual models, high‑accuracy cloud services, translation solutions, legal applications, and integration into smart devices.
This article examines the current landscape of intelligent voice technology—including speech recognition, synthesis, voiceprint identification, and acoustic event detection—highlighting technical hurdles, evaluation metrics, recent advances such as WaveNet, and a wide range of practical applications from mobile devices to smart hardware and enterprise solutions.
The article surveys Tencent’s recent advances in smart‑speaker voice interaction, detailing a full technology chain—from front‑end capture, wake‑up and enhancement, through speaker verification and short‑speech voiceprint, to TDNN/LSTM speech recognition, target speaker extraction, and end‑to‑end attention modeling for robust, personalized performance.
The talk reviews how massive speech data, faster GPUs/CPUs, and deep‑learning models such as DNN, LSTM, CNN, and end‑to‑end CTC have dramatically boosted speech‑recognition accuracy, while outlining remaining challenges like noise, accents, far‑field and multi‑speaker scenarios and describing Tencent Cloud’s related services.
iQIYI HomeAI tackles the bottleneck of static language models in voice assistants by separating phonetic and semantic processing, correcting ASR errors at the intent‑recognition layer with pinyin‑enhanced entity correction, thereby reducing error amplification in video‑on‑demand interactions and paving the way for adaptive, personalized voice experiences.
Alibaba’s post‑doctoral program connects PhDs with massive industry data and real‑world projects, showcasing how researchers like Xue Shaofei and Pei Changhua develop cutting‑edge speech‑recognition, scheduling and recommendation technologies that directly impact millions of users.
AIIndustry-Academia CollaborationPostdoctoral Research
Didi’s attention‑based end‑to‑end Mandarin speech recognizer, built on the Listen‑Attend‑Spell architecture and modeling roughly 5,000 common characters, delivers 15‑25% relative accuracy gains over its prior LSTM‑CTC system while cutting model size, latency and server requirements and simplifying training by eliminating separate acoustic, pronunciation and language components.
This guide walks developers through adding WeChat’s free AI translation plugin to a mini‑program, covering plugin installation, voice input, real‑time transcription, text translation, and speech synthesis in five straightforward steps, complete with code snippets and configuration details.
In this interview, Long Mingkang, Vice President of iFlytek's Cloud Computing Institute, shares his experience building large‑scale speech cloud services, discusses the technical hurdles of speech recognition and AI platform development, compares TensorFlow and MXNet, and offers insights on AutoML, industry trends, and how engineers can master AI.
The article reports on Liulishuo’s participation in Interspeech 2017 and the SLaTE 2017 workshop, summarizing key research papers on noise‑robust ASR, attention‑based models, TensorFlow training, modern TTS systems, speaker identification datasets, and includes a hiring announcement for AI engineers.
This article explains how improved latency‑controlled BLSTM acoustic models can boost online speech‑recognition accuracy while cutting decoding computation, detailing two model refinements that achieve 40‑60% speed gains with minimal loss in recognition performance.
This article explains how latency‑controlled BLSTM acoustic models were refined to accelerate online speech recognition while preserving accuracy, detailing the training strategy, computational trade‑offs, and two model enhancements that achieve up to 60% faster decoding with modest resource savings.
The article announces the open‑source release of kaldi‑ctc, a GPU‑accelerated CTC‑based end‑to‑end speech recognition toolkit built on Kaldi, warp‑ctc and cuDNN, highlighting its 5‑6× training speedup, real‑time decoding factor of 0.02, and performance comparisons on the LibriSpeech corpus.
The Interspeech 2016 conference in San Francisco showcased major advances in speech recognition, synthesis, far‑field processing, and language modeling, highlighting CTC extensions, deep CNN innovations, WaveNet’s generative audio, and new techniques for multi‑microphone acoustic modeling.
This article walks through the design and implementation of a voice‑controlled music iOS application using Siri SDK, Sketch and Principle for UI prototyping, and Xcode with Objective‑C and SpeechKit for speech recognition, culminating in a functional prototype that searches iTunes and plays song previews.
iFLY’s Mobile Speech Platform (MSP) integrates cloud‑based speech recognition and text‑to‑speech technologies to deliver high‑quality, multi‑channel voice services for Android, iOS and other devices, detailing its four‑layer architecture, core functionalities, and the role of ASR and TTS in modern human‑machine interaction.