0 views collected around this technical thread.
Senior algorithm engineer Qi Jianwei from Xiaomi presents a comprehensive overview of building a large‑model‑centric Agent framework for voice assistants, covering prompt design, information retrieval, RAG processes, and future optimization directions to enhance performance and stability.
This article presents an in‑depth overview of NLP techniques used in voice assistants, covering the end‑to‑end conversational AI pipeline, intent and slot modeling, multi‑turn dialog management, model deployment pipelines, quantization methods, and self‑learning strategies for continuous improvement.
This article presents a comprehensive evaluation framework for OPPO's XiaoBu AI assistant, covering evaluation concepts, objectives, five key elements, sampling methods, dimension selection, annotation scoring, report generation, and a detailed Q&A that illustrates practical metrics and processes for voice and search services.
This article presents a comprehensive evaluation framework for OPPO's XiaoBu AI assistant, covering the concept and purpose of evaluation, the five key evaluation elements, data sampling strategies, dimension and rule selection, annotation scoring, reporting guidelines, and detailed procedures for assessing wake‑up, ASR, NLU, and TTS performance.
This article presents the business background of Tmall Genie’s voice‑driven content‑on‑demand service, critiques the traditional pipeline for entity extraction, and details an end‑to‑end speech‑semantic model—including the Speech2Slot architecture, knowledge‑enhanced encoding, and Phoneme‑BERT unsupervised pre‑training—demonstrating significant performance gains in both generation and classification tasks.
This guide explains step‑by‑step methods for iPhone and Android users to instantly open their health code using Siri shortcuts, double‑tap back gestures, home‑screen shortcuts, and voice assistants, improving efficiency during pandemic‑related checks.
This article evaluates classic Siamese networks, various BERT‑based pretrained models, and several training tricks such as adversarial training, k‑fold cross‑validation, and model ensembling on both a public similarity‑sentence competition dataset and an internal voice‑assistant standard question matching dataset, ultimately raising accuracy from 97.23 % to 99.5 %.
The document details DiDi’s driver‑side intelligent voice assistant “XiaoDi,” describing its three‑layer architecture—audio source switching controller, semantic‑parsing core, and business API—along with conflict‑resolution mechanisms, multi‑turn dialogue handling, and a four‑region UI design that together enhance driver safety, convenience, and well‑being.
This article explores the current state of AI, the evolution of NLP and voice assistants, common pitfalls in AI product development, and practical product‑management methods—including user segmentation, metric design, and lifecycle planning—to help engineers and product managers deliver effective AI‑driven solutions.
The article details the design and implementation of Xiaomi's music‑focused natural language understanding platform, covering its service architecture, intent extraction, knowledge‑base search, slot filling, personalization, and the specific data and modeling challenges encountered.
The article provides a detailed technical breakdown of Google Duplex, explaining how its speech recognition, natural language understanding, dialogue management, and speech synthesis modules work together to produce task‑oriented, natural‑sounding conversations and discussing challenges such as handling refusals, conditional responses, context management, and future scalability and safety concerns.
The article introduces MISA, Ant Financial’s AI‑driven voice service assistant that uses deep‑learning models such as CNN and RNN for problem guessing, identification, and interactive clarification, details its system components and evaluation metrics, and describes the related AI competition focused on sentence‑similarity calculation.
The author reflects on attending AWS re:Invent 2017, highlighting Alexa's AI capabilities, the ecosystem for skill development, the technical challenges of building voice assistants, and the need for tight integration of product, algorithm, and engineering to advance intelligent assistants.