3,135 articles
Spectrum of a sentence
The spectrum of a sentence is the set of sizes of its finite models, introduced by Heinrich Scholz in 1952; first-order spectra are exactly the NEXPTIME sets.
Speech activity detection
Speech activity detection (SAD), also called voice activity detection (VAD), is a signal processing method that separates speech from silence and noise in audio, frame by frame.
Speech recognition
Speech recognition, also called automatic speech recognition or speech to text, converts an audio signal of spoken language into a text transcript, measured by word error rate.
Speech separation
Speech separation is the signal processing and machine learning task of recovering individual speech signals from an audio mixture, underpinning speech recognition, mobile communication, and hearing aids.
Speech translation
Speech translation converts spoken utterances in one language into text or speech in another, combining speech recognition with machine translation; uses include travel, lectures, dubbing, and crisis response.
Speech-to-speech translation
Speech-to-speech translation translates spoken utterances into another language so speakers can converse, through cascades of recognition, translation, and synthesis, or direct models like Translatotron, first shown in 2019.
Speeded-up robust features
Speeded-up robust features (SURF) is a scale- and rotation-invariant local feature detector and descriptor that matches interest points across images, introduced in 2006 as a faster alternative to SIFT.
Spell checker
A spell checker is software that identifies misspelled words and suggests corrections, found in word processors, browsers, and search engines since Ralph Gorin's 1971 SPELL program.
Spelling correction
Spelling correction is the automatic detection of misspelled words in text and selection of a replacement, a natural language processing task dating to the early 1960s.
Spider monkey optimization
Spider monkey optimization (SMO) is a swarm intelligence metaheuristic for continuous numerical optimization, introduced by Jagdish Chand Bansal and colleagues in 2014, modeling the fission–fusion foraging of spider monkeys.
Spiking neural network
A spiking neural network (SNN) is a neural network in which neurons communicate by discrete all-or-nothing pulses called spikes, often called a third generation of neural networks.
Spinlock
A spinlock is a mutual exclusion lock where a waiting thread busy-waits by repeatedly checking the lock, efficient for critical sections shorter than a context switch.
Splay tree
A splay tree, also called a self-adjusting binary search tree, is a search tree that splays each accessed node to the root, giving amortized O(log n) operations.
Spline interpolation
Spline interpolation, or interpolating spline, fits a low-degree piecewise polynomial, usually cubic, through data points with smooth joins at the knots, avoiding the wild oscillations of single high-degree polynomials; I. J. Schoenberg introduced it in 1946.
Split federated learning
Split federated learning (SFL) is a distributed machine learning method that splits a neural network between clients and a server, introduced by Chandra Thapa and colleagues in 2020.
Split learning
Split learning is a distributed machine learning technique, developed at the MIT Media Lab in 2018, that partitions a neural network between clients and a server.
Splunk
Splunk is a software platform that ingests, indexes, and searches machine-generated data like logs and security events; Cisco acquired it for about $28 billion in 2024.
SQL
SQL, or Structured Query Language, is the standard language for defining, querying, and controlling data in relational databases, developed at IBM in 1974 and standardized by ISO and ANSI.
SQL injection
SQL injection (SQLIA), also known as Structured Query Language injection, is a code injection attack where user input is interpreted as SQL code rather than data, letting attackers extract or alter database contents.
SQL Server Express
SQL Server Express, also known as Microsoft SQL Server Express, is the free edition of Microsoft SQL Server, limited to 4 cores, 1,410 MB of memory, and 50 GB per database.
SQL Server Integration Services
SQL Server Integration Services (SSIS) is a Microsoft platform for building data integration and ETL solutions for data warehousing, replacing DTS and now also hosted in Azure.
SQL standardization
SQL standardization defines the SQL database language as the international standard ISO/IEC 9075, first published by ANSI in 1986 and adopted by ISO in 1987.
SQL:1999
SQL:1999, also known as SQL3, is the third generation of the SQL database language standard, published in December 1999 with object technology its headline addition.
SQL/PGQ
SQL/PGQ (ISO/IEC 9075-16:2023) is Part 16 of SQL:2023, defining property graph creation over relational tables and GRAPH_TABLE pattern matching; implemented in Oracle 23ai and DuckPGQ, reverted from PostgreSQL 19.
SQLGlot
SQLGlot is a dependency-free Python SQL parser, transpiler, optimizer, and engine by Toby Mao, translating between 30+ dialects such as DuckDB, Spark, Snowflake, and BigQuery via a recursive descent parser and AST.
SQLite
SQLite is a self-contained, serverless, transactional SQL database engine stored in a single cross-platform disk file, with no separate server process, and its code is public domain.
SQLMesh
SQLMesh is an open source SQL/Python data transformation framework by Tobiko Data, later Fivetran and the Linux Foundation. Known for SQLGlot semantic parsing, Terraform-style plan/apply, virtual environments, and dbt compatibility.
Squeeze-and-Excitation network
The Squeeze-and-Excitation network (SENet) is a convolutional neural network architecture proposed in September 2017 by Hu et al. that recalibrates channel-wise feature responses via its SE block, winning ILSVRC 2017.
Squirrel search algorithm
The squirrel search algorithm (SSA) is a nature-inspired metaheuristic for continuous and engineering optimization, introduced by Mohit Jain, Vijander Singh, and Asha Rani in 2018.
SSD (object detection)
SSD (Single Shot MultiBox Detector) is a one-stage object detection neural network that predicts object classes and bounding boxes in a single pass, introduced in 2015.